© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9558
    Prev
    Next
    INDEX
    Explanations

    words starting with H

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

    words starting with '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_40_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
     fortn
    0.40
    ananti
    0.39
     décrire
    0.39
    nment
    0.39
     dumplings
    0.38
    ି
    0.38
    igators
    0.38
    ᔨ
    0.38
     resettlement
    0.38
    ferred
    0.37
    POSITIVE LOGITS
     H
    0.98
    H
    0.80
    aphazard
    0.79
    ottest
    0.74
    itherto
    0.73
    élène
    0.73
     হ
    0.68
    indsight
    0.68
    omicide
    0.68
    osiery
    0.68
    Activations Density 0.250%

    No Known Activations