© 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. 14849
    Prev
    Next
    INDEX
    Explanations

    future results

    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
     Embro
    0.70
     keyword
    0.68
     KeyError
    0.68
     Fitting
    0.67
    접
    0.67
     fitting
    0.66
    ifting
    0.66
     বৎসর
    0.66
     past
    0.65
    െടു
    0.64
    POSITIVE LOGITS
    occurrence
    0.70
     அக்க
    0.70
     qualcuno
    0.67
    Sorry
    0.67
     분포
    0.64
    জম
    0.64
    cón
    0.64
    ঈ
    0.63
     trends
    0.63
     ఆరోగ
    0.63
    Activations Density 0.000%

    No Known Activations