© 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
    2. Gemma-3-12B
    3. 41-GEMMASCOPE-2-RES-65K
    4. 14898
    Prev
    Next
    INDEX
    Explanations

    finger

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
     Calhoun
    0.60
    சோ
    0.55
     sovr
    0.53
    포츠
    0.52
    ាវ
    0.52
    亭
    0.51
    欹
    0.51
    Archives
    0.51
     वाद
    0.50
     Granville
    0.50
    POSITIVE LOGITS
     finger
    5.31
     Finger
    5.03
    Finger
    5.03
    finger
    4.94
     fingers
    4.72
     Fingers
    4.31
    指
    4.28
     fingerprint
    4.22
    fing
    3.94
     fingert
    3.92
    Activations Density 0.087%

    No Known Activations