© 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. 53231
    Prev
    Next
    INDEX
    Explanations

    explores possible futures

    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
     ambitions
    0.47
     chefs
    0.47
     blinds
    0.44
     trainers
    0.43
     अ
    0.42
     Accountants
    0.42
    <unused2140>
    0.42
     ل
    0.41
     आरा
    0.41
     ล
    0.41
    POSITIVE LOGITS
     cerebrospinal
    0.46
    тельстве
    0.44
    pressure
    0.40
    óstico
    0.39
    étation
    0.38
     resistência
    0.38
    Marker
    0.38
    acial
    0.38
     আর্থিক
    0.38
    aspetto
    0.38
    Activations Density 0.001%

    No Known Activations