© 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. 18379
    Prev
    Next
    INDEX
    Explanations

    specific nouns and concepts

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

    human condition

    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
     Se
    0.40
     Bhar
    0.40
    fq
    0.39
     Ә
    0.39
     sorprendente
    0.39
     Desire
    0.38
     Ratt
    0.38
    ktionen
    0.38
     Chris
    0.37
     fratt
    0.37
    POSITIVE LOGITS
    ясплат
    0.48
    형
    0.44
    как
    0.44
     playbook
    0.43
    г
    0.41
    чик
    0.41
     armband
    0.41
    楤
    0.40
    인
    0.40
    ’
    0.39
    Activations Density 0.756%

    No Known Activations