© 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. 41568
    Prev
    Next
    INDEX
    Explanations

    specific entities followed by details

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

    needs. attempt. is a. Not Lewis. Tropes. Beyond demographics. files. V.O. which. Thinking of

    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
    igating
    0.46
    нков
    0.46
    }{\
    0.45
    صیل
    0.45
     datatype
    0.45
    চ্ছিলাম
    0.44
    linecap
    0.44
    ugal
    0.43
     peculiarity
    0.43
    蹌
    0.43
    POSITIVE LOGITS
     Kunden
    0.48
     Doodle
    0.48
    räume
    0.46
    jęcia
    0.46
     ove
    0.46
     Oscill
    0.46
    히려
    0.46
     Allemagne
    0.45
     Vertrags
    0.45
    プロセス
    0.45
    Activations Density 0.000%

    No Known Activations