Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 35
    Prev
    Next
    INDEX
    Explanations

    possessive nouns followed by 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_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
    P
    0.85
    U
    0.78
    S
    0.77
    ان
    0.74
    C
    0.74
    H
    0.72
    R
    0.72
    Y
    0.72
    ка
    0.70
    L
    0.68
    POSITIVE LOGITS
     shortcomings
    0.94
     antics
    0.93
     own
    0.91
     burgeoning
    0.88
     penchant
    0.86
     rightful
    0.86
     respective
    0.84
     expansive
    0.84
     offerings
    0.83
     inherent
    0.83
    Activations Density 0.438%

    No Known Activations