© 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. 202288
    Prev
    Next
    INDEX
    Explanations

    differentiate situations

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

    answering questions

    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
     hearings
    0.47
    (!
    0.45
     φι
    0.45
    (\
    0.44
     chúng
    0.42
    Hs
    0.42
     .
    0.41
    íp
    0.41
    families
    0.41
    热爱
    0.41
    POSITIVE LOGITS
    сен
    0.55
    िस
    0.51
     gubit
    0.51
    सो
    0.49
    ーン
    0.49
     pierde
    0.49
    oviruses
    0.49
    런치
    0.49
     abscess
    0.48
    ミックス
    0.48
    Activations Density 0.001%

    No Known Activations