© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7606
    Prev
    Next
    INDEX
    Explanations

    is best

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chaleur
    0.43
     puncak
    0.43
    酤
    0.41
    नोमियल
    0.41
     ryzy
    0.41
    परेशन
    0.40
    <unused8>
    0.40
     zegt
    0.40
    ญิง
    0.40
    飲料
    0.40
    POSITIVE LOGITS
    is
    0.45
     V
    0.45
     N
    0.45
    -
    0.44
     L
    0.43
     EL
    0.43
     O
    0.43
     AC
    0.43
     Hyper
    0.42
     Hex
    0.42
    Activations Density 0.002%

    No Known Activations