© 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-65K
    7. 764
    Prev
    Next
    INDEX
    Explanations

    placeholders and greetings

    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_65k_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
     excre
    0.65
     macroscopic
    0.65
     transcendent
    0.65
     immutable
    0.63
     hermaph
    0.63
    })}
    0.62
     physiologically
    0.61
     deterministic
    0.61
     primordial
    0.61
     trillions
    0.61
    POSITIVE LOGITS
     আমাদের
    1.01
     グ
    0.95
    我們
    0.91
     [
    0.90
     למ
    0.90
     nuestro
    0.89
     {[
    0.88
     нашей
    0.87
     マ
    0.86
     हाम्रो
    0.82
    Activations Density 1.046%

    No Known Activations