© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 97011
    Prev
    Next
    INDEX
    Explanations

    holding a hand

    np_acts-logits-general · gemini-2.5-flash-lite

    touching hands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     fingertips
    0.52
     chopsticks
    0.47
     fingert
    0.47
     fingers
    0.46
     hugging
    0.46
    搂
    0.44
     আঙ্গ
    0.42
     तकनीक
    0.42
     gripper
    0.42
    👢
    0.42
    POSITIVE LOGITS
    Hospital
    0.46
    CSR
    0.46
     hospital
    0.43
    Davidson
    0.42
    Corporate
    0.42
    ላለ
    0.42
    Curs
    0.42
     hospitalized
    0.41
    Southern
    0.40
     Curb
    0.39
    Activations Density 0.046%

    No Known Activations