© 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. 2269
    Prev
    Next
    INDEX
    Explanations

    because nums

    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
    놁
    0.67
    ዎን
    0.64
    Bitte
    0.61
     filóso
    0.61
     konusunda
    0.61
    utherford
    0.60
    Nicht
    0.59
    <unused764>
    0.59
    functie
    0.58
     precedente
    0.58
    POSITIVE LOGITS
     The
    0.46
     I
    0.45
     there
    0.45
     they
    0.45
     we
    0.43
     everyone
    0.42
     it
    0.42
     Pot
    0.41
     All
    0.41
     Every
    0.40
    Activations Density 0.001%

    No Known Activations