© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14206
    Prev
    Next
    INDEX
    Explanations

    bandwidth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ة
    2.35
    язку
    2.32
    ೇತ್ರ
    2.31
    ંટ
    2.26
    гістра
    2.25
    ції
    2.24
    herjee
    2.24
    ionate
    2.24
    istä
    2.16
    祇
    2.15
    POSITIVE LOGITS
    ল
    3.14
    իմ
    2.66
    десят
    2.65
    م
    2.63
    न
    2.61
    োম
    2.59
    memberNameLink
    2.58
    BUUID
    2.58
    ల్
    2.57
     indiqu
    2.53
    Activations Density 0.000%

    No Known Activations