© 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. 194525
    Prev
    Next
    INDEX
    Explanations

    award winning

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

    create a draft

    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
     cinematographer
    0.48
    ঞ্জেল
    0.47
    ちゃんと
    0.46
    늑
    0.44
    HIGHLIGHT
    0.43
     collapsible
    0.42
    fbox
    0.42
    予め
    0.40
    んと
    0.40
    Tur
    0.40
    POSITIVE LOGITS
     videre
    0.55
    aks
    0.47
     tek
    0.46
     erf
    0.46
    gia
    0.46
     disse
    0.46
    ̧
    0.45
    uder
    0.44
     Brett
    0.44
    inkler
    0.44
    Activations Density 0.000%

    No Known Activations