© 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. 30141
    Prev
    Next
    INDEX
    Explanations

    because `fiscal` `strlen` `match` `tuple`

    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
    इये
    0.43
    calup
    0.43
    anjutnya
    0.41
    阙
    0.40
     رہ
    0.39
     nucl
    0.39
    wahati
    0.39
    🔛
    0.38
     の
    0.38
    kkue
    0.37
    POSITIVE LOGITS
     because
    0.44
     karena
    0.43
    ط
    0.42
     fordi
    0.42
     لأنه
    0.42
    因为
    0.41
    因為
    0.40
    SHA
    0.40
    because
    0.40
    OMA
    0.40
    Activations Density 0.000%

    No Known Activations