© 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-16K
    7. 10104
    Prev
    Next
    INDEX
    Explanations

    making a point

    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_16k_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
    ટક
    0.63
     कर्
    0.63
     بسم
    0.55
    ణం
    0.55
    SQL
    0.55
     Latham
    0.53
     пада
    0.53
    σ
    0.52
    })\
    0.52
    Mis
    0.51
    POSITIVE LOGITS
     point
    4.20
    point
    3.72
     Point
    3.72
    Point
    3.55
     POINT
    3.36
     punto
    3.36
     points
    3.09
    POINT
    3.02
     Points
    2.84
    points
    2.77
    Activations Density 0.092%

    No Known Activations