© 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. 21983
    Prev
    Next
    INDEX
    Explanations

    H followed by letters

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

    words starting with H or h

    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
    WholeProgram
    0.45
    姦
    0.42
     ล
    0.39
    頒
    0.39
    urètre
    0.38
    efois
    0.36
    ẵn
    0.36
    دیای
    0.36
     provoque
    0.36
    Iraq
    0.35
    POSITIVE LOGITS
     HL
    0.58
     H
    0.56
     h
    0.55
     HC
    0.54
     HU
    0.52
     HSP
    0.51
     HX
    0.50
     HM
    0.49
     HCC
    0.48
     HV
    0.48
    Activations Density 0.261%

    No Known Activations