© 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. 5599
    Prev
    Next
    INDEX
    Explanations

    transferable information

    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
    aholic
    0.41
    Bronze
    0.39
    bron
    0.39
    یک
    0.38
    goog
    0.38
    ━━
    0.38
    uttered
    0.38
    stantial
    0.38
    --
    0.37
    cher
    0.36
    POSITIVE LOGITS
     TRANSFER
    0.50
     CIRCUIT
    0.47
     Einst
    0.47
     EXAMINATION
    0.45
     transferable
    0.43
     EIS
    0.43
     DBT
    0.43
     Transfer
    0.42
     SERVICE
    0.41
     Pé
    0.40
    Activations Density 0.001%

    No Known Activations