© 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-65K
    7. 10840
    Prev
    Next
    INDEX
    Explanations

    from location or state

    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_65k_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
    belum
    0.47
     unprocessed
    0.45
    別途
    0.44
    ዎ
    0.43
    ܂
    0.43
     ఎక్కువ
    0.42
    VOID
    0.41
     إنشاء
    0.41
    猕
    0.41
    මක්
    0.41
    POSITIVE LOGITS
     khỏi
    0.74
     clutches
    0.52
    orbit
    0.49
     orbit
    0.49
     confines
    0.48
     Киє
    0.48
     thence
    0.47
    ر
    0.45
     premises
    0.44
     moor
    0.43
    Activations Density 0.073%

    No Known Activations