© 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. 3708
    Prev
    Next
    INDEX
    Explanations

    Revolut hops, `if` keywords

    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
    ure
    0.45
    besie
    0.44
    ia
    0.44
    orno
    0.44
    闹
    0.44
    形態
    0.43
     થાય
    0.43
    òa
    0.43
     Kyoto
    0.42
    reif
    0.42
    POSITIVE LOGITS
    ский
    0.51
     aldı
    0.50
    හ
    0.50
    ışı
    0.49
     powin
    0.47
    सामाजिक
    0.47
    Gruß
    0.46
     sami
    0.46
     así
    0.46
    H
    0.46
    Activations Density 0.001%

    No Known Activations