© 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. 34954
    Prev
    Next
    INDEX
    Explanations

    salary estimates

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

    salary and pay estimates

    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
    inot
    0.40
    渇
    0.39
     holes
    0.39
    ったり
    0.38
    க்கண
    0.38
     tabletop
    0.37
    緒
    0.37
     tat
    0.36
     digest
    0.36
     revisions
    0.36
    POSITIVE LOGITS
     estimado
    0.46
    posing
    0.45
    व्ह
    0.44
    estimating
    0.43
     Estim
    0.42
     주는
    0.41
     $=\
    0.41
    CellValue
    0.40
     }</
    0.40
     옳은
    0.40
    Activations Density 0.001%

    No Known Activations