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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 7619
    Prev
    Next
    INDEX
    Explanations

    bill difference amount

    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
     ball
    0.67
    istic
    0.66
     pond
    0.65
     탱크
    0.65
     quot
    0.63
     flotte
    0.63
     lith
    0.62
    桑
    0.61
    வும்
    0.60
     spect
    0.60
    POSITIVE LOGITS
    urator
    0.77
    Gradle
    0.72
    ibin
    0.70
    бовать
    0.66
    jego
    0.64
    Candidates
    0.63
    Unexpected
    0.63
    ţin
    0.62
    üre
    0.61
    Sergio
    0.61
    Activations Density 0.684%

    No Known Activations