© 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. 247758
    Prev
    Next
    INDEX
    Explanations

    local listings

    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
     countrymen
    0.51
    u
    0.45
     коли
    0.44
     فات
    0.44
     Exchequer
    0.43
     Present
    0.42
    ர்ப்ப
    0.42
     RSVP
    0.42
    vegan
    0.42
    </li>
    0.42
    POSITIVE LOGITS
    молча
    0.56
    ᔪ
    0.53
    आइ
    0.48
    𝔱
    0.48
    ：（
    0.47
    }$-(
    0.47
    ৪৩
    0.46
    ণির
    0.46
    𝔞
    0.46
    دید
    0.46
    Activations Density 0.000%

    No Known Activations