© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 184775
    Prev
    Next
    INDEX
    Explanations

    here at / world at / stuff Brad / very good / laws share / well with / chance to / legends go / developers along / officials more

    np_acts-logits-general · gemini-2.5-flash-lite

    naming characters and settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    로부터
    0.52
    로서
    0.47
    दिल्ली
    0.47
    𝓰
    0.46
    placed
    0.45
    posizione
    0.45
    У
    0.44
    ု
    0.44
    )\|_{\
    0.43
    ᱓
    0.43
    POSITIVE LOGITS
     bere
    0.53
     engen
    0.51
     darunter
    0.49
     kla
    0.49
     verl
    0.48
     juillet
    0.47
     kosten
    0.47
     passen
    0.47
     awhile
    0.47
     ########.
    0.47
    Activations Density 0.001%

    No Known Activations