© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 7586
    Prev
    Next
    INDEX
    Explanations

    reporting speech

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
    О
    1.04
    ため
    1.02
    А
    0.97
    通り
    0.92
    ীয়
    0.92
    Thể
    0.91
    а
    0.90
    К
    0.90
    Selain
    0.90
    含む
    0.86
    POSITIVE LOGITS
     goodbye
    1.44
     hello
    1.15
     nothing
    1.12
     embl
    1.08
    tions
    1.07
     anything
    1.01
     NOTHING
    0.97
    finding
    0.96
     inget
    0.96
     brou
    0.94
    Activations Density 0.005%

    No Known Activations