© 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. 250843
    Prev
    Next
    INDEX
    Explanations

    checking portal

    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
    ອດ
    0.44
    곁
    0.43
     erythe
    0.43
    también
    0.43
    lás
    0.42
    aphyl
    0.42
     carcinomas
    0.42
    apopt
    0.42
    རྒྱ
    0.42
    酵素
    0.42
    POSITIVE LOGITS
    Custom
    0.46
     Custom
    0.45
    EventListener
    0.42
     ∣
    0.41
     –
    0.40
     Colonial
    0.38
     sundry
    0.38
     spéciaux
    0.38
     portals
    0.38
     |-
    0.38
    Activations Density 0.001%

    No Known Activations