© 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. 182707
    Prev
    Next
    INDEX
    Explanations

    covered" means helped

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

    review analysis and election news

    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
    chang
    0.51
    ím
    0.47
     удовлетво
    0.45
    uum
    0.43
    </strong>
    0.43
    satisf
    0.43
     veio
    0.43
    chu
    0.42
    ness
    0.42
    veys
    0.42
    POSITIVE LOGITS
    ই
    0.46
    বিশেষ
    0.45
     ormai
    0.44
     ஸ்
    0.44
    ስ
    0.44
    Ens
    0.44
     Sark
    0.43
    ิง
    0.43
     প্রস্তুত
    0.43
    Offset
    0.42
    Activations Density 0.000%

    No Known Activations