© 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. 124278
    Prev
    Next
    INDEX
    Explanations

    career change

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

    more, impact, feeling, goal, why, role, believed

    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
    Cath
    0.56
    2
    0.55
    Book
    0.51
     Gile
    0.50
    .
    0.49
     Cath
    0.49
     Luci
    0.46
    Export
    0.46
     penta
    0.45
     Lido
    0.45
    POSITIVE LOGITS
    กร
    0.47
    ர்ந்த
    0.45
    рых
    0.45
     vacanam
    0.44
    வ
    0.44
    ர
    0.43
     décrit
    0.43
     shortlist
    0.43
     Descripción
    0.42
    დე
    0.42
    Activations Density 0.000%

    No Known Activations