© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 24245
    Prev
    Next
    INDEX
    Explanations

    index finger

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    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
     bookcases
    0.42
    marshalN
    0.38
    胴
    0.38
    濩
    0.38
    觚
    0.38
     Lagoon
    0.37
    nés
    0.37
    থানি
    0.37
    宇
    0.36
     উভয়
    0.36
    POSITIVE LOGITS
     finger
    2.38
     fingers
    2.13
     Finger
    1.98
    Finger
    1.93
    指
    1.86
    finger
    1.83
     fingert
    1.82
     Fingers
    1.77
     fingertips
    1.71
     doigt
    1.68
    Activations Density 0.008%

    No Known Activations