© 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. 88164
    Prev
    Next
    INDEX
    Explanations

    sometimes will, instead

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

    presence filling conversations hero thinking

    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
     Freed
    0.48
     Excess
    0.46
     Гуляць
    0.45
    稜
    0.44
    らなかった
    0.43
    裕
    0.43
     ktore
    0.43
     сказала
    0.43
    HttpResponse
    0.42
    ろし
    0.42
    POSITIVE LOGITS
     chiff
    0.54
     cinch
    0.52
     champagne
    0.48
     tata
    0.47
     cinema
    0.46
     abgesch
    0.46
     collapsible
    0.46
    temperatur
    0.46
     gond
    0.45
    ⊂
    0.45
    Activations Density 0.001%

    No Known Activations