© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3206
    Prev
    Next
    INDEX
    Explanations

    experience descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Alejandra
    1.91
    agata
    1.83
     requestCode
    1.82
    ₁+
    1.79
    AndKeys
    1.79
    nikova
    1.79
     încep
    1.73
     respuestas
    1.72
     Nagano
    1.72
    addassa
    1.69
    POSITIVE LOGITS
     the
    1.80
    the
    1.63
     him
    1.40
     a
    1.25
     is
    1.24
     on
    1.22
     he
    1.21
     el
    1.19
     his
    1.18
     it
    1.18
    Activations Density 0.059%

    No Known Activations