© 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. 34884
    Prev
    Next
    INDEX
    Explanations

    fitting including

    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
     divisive
    0.47
    य
    0.43
    overall
    0.42
    ll
    0.42
    timing
    0.41
    pools
    0.41
    here
    0.40
    heres
    0.39
     poolside
    0.39
    о
    0.39
    POSITIVE LOGITS
     adqu
    0.42
     اكت
    0.41
     Specimens
    0.39
     습
    0.39
     edição
    0.39
     Ressources
    0.39
     vorige
    0.39
     Metode
    0.39
     Trabajo
    0.39
     Doi
    0.39
    Activations Density 0.007%

    No Known Activations