© 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. 14212
    Prev
    Next
    INDEX
    Explanations

    states and descriptions

    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
    <unused2197>
    0.94
    <unused2172>
    0.92
     myriad
    0.92
     camaraderie
    0.91
     distinctions
    0.90
     stipulations
    0.89
    他說
    0.87
     hoops
    0.87
    <unused2130>
    0.86
     folks
    0.86
    POSITIVE LOGITS
     considered
    1.31
     regarded
    1.27
     loosing
    1.24
     being
    1.24
     denoted
    1.24
     located
    1.24
     placed
    1.23
     NOT
    1.19
     composed
    1.18
     unable
    1.16
    Activations Density 0.059%

    No Known Activations