© 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. 26896
    Prev
    Next
    INDEX
    Explanations

    within specific contexts

    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
    èse
    0.41
    APK
    0.40
    zione
    0.40
    izzazione
    0.40
    zj
    0.39
    skij
    0.38
    wark
    0.37
    荆
    0.37
     Domains
    0.36
    ORMAL
    0.35
    POSITIVE LOGITS
     yazı
    0.47
     nacionais
    0.46
    американ
    0.46
     nível
    0.45
    город
    0.44
    潾
    0.43
     nivel
    0.43
     integração
    0.43
    umably
    0.42
    ри
    0.42
    Activations Density 0.000%

    No Known Activations