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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-65K
    4. 442
    Prev
    Next
    INDEX
    Explanations

    asking or responding about self

    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
     culminates
    0.67
     خبرگزاری
    0.66
    тип
    0.66
    స్థ
    0.65
    انو
    0.64
    netz
    0.64
    empot
    0.64
    а
    0.63
    分散
    0.63
    помним
    0.62
    POSITIVE LOGITS
     আমি
    1.74
     मैं
    1.65
     I
    1.60
    私は
    1.58
     μου
    1.56
     tôi
    1.55
     मुझे
    1.54
     我
    1.52
     நான்
    1.52
     Alright
    1.51
    Activations Density 0.447%

    No Known Activations