© 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. 14784
    Prev
    Next
    INDEX
    Explanations

    followed by a list items

    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
     refers
    0.84
     affirme
    0.78
     Texte
    0.76
     является
    0.76
     represents
    0.76
     ")";
    0.75
    ܂
    0.71
     texte
    0.66
     данном
    0.66
    ிகளும்
    0.65
    POSITIVE LOGITS
     kinds
    1.04
    :',
    0.88
    :</
    0.85
    𝙢
    0.84
    riteria
    0.84
     types
    0.83
    पैकी
    0.82
    :<
    0.82
    :**
    0.80
     keys
    0.80
    Activations Density 0.044%

    No Known Activations