© 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. 55925
    Prev
    Next
    INDEX
    Explanations

    advocate for, course of, needed

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

    explaining requirements or states

    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
     BECAUSE
    0.46
    DO
    0.42
     Amtrak
    0.41
    $
    0.41
     SAV
    0.41
     at
    0.41
     interfere
    0.40
    NOW
    0.39
     IN
    0.39
    激安
    0.39
    POSITIVE LOGITS
     parámetro
    0.49
    玽
    0.47
    qualiter
    0.46
    ᅴ
    0.46
    ismod
    0.46
    Dihydro
    0.46
    しくは
    0.45
    㶱
    0.45
    ديث
    0.45
    yecto
    0.45
    Activations Density 0.001%

    No Known Activations