© 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. 61558
    Prev
    Next
    INDEX
    Explanations

    specific descriptive words

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

    versus or alternatives

    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
     Casi
    0.45
     поможет
    0.44
     Kijk
    0.44
     ferrovi
    0.44
     Approve
    0.42
    駆
    0.39
     indiquant
    0.39
     inoxid
    0.39
     Merkezi
    0.39
     Denote
    0.38
    POSITIVE LOGITS
     maupun
    0.61
     alone
    0.60
    alone
    0.59
    Vs
    0.56
    以及
    0.55
    만
    0.54
    以外の
    0.53
    +
    0.52
    だけでなく
    0.52
    뿐
    0.52
    Activations Density 0.208%

    No Known Activations