© 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. 90573
    Prev
    Next
    INDEX
    Explanations

    sensitive information

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

    presenting choices for

    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
    art
    0.61
    ad
    0.55
    adia
    0.51
    emas
    0.49
    endem
    0.48
    att
    0.47
    ح
    0.47
    ann
    0.47
    anh
    0.47
    pat
    0.46
    POSITIVE LOGITS
     やっ
    0.46
     ໜອງ
    0.46
     dwRes
    0.46
    '])]
    0.46
    ~)
    0.46
    *',
    0.45
    ()))
    0.44
    ']]
    0.44
    ]][
    0.44
    괜
    0.44
    Activations Density 0.001%

    No Known Activations