© 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. 99174
    Prev
    Next
    INDEX
    Explanations

    units or components

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

    beyond expectationsloss of innocencedelivering solutionsdetecting issuesgone now

    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
     enlarging
    0.54
     enlarge
    0.50
     Fringe
    0.47
    డీ
    0.45
     Observations
    0.44
     enlarged
    0.44
    迳
    0.43
     Treated
    0.43
     eines
    0.43
    忪
    0.43
    POSITIVE LOGITS
    Could
    0.47
     女
    0.46
    ikian
    0.43
     高
    0.42
     genitori
    0.42
     शुर
    0.42
    Activ
    0.42
    <unused545>
    0.42
    lic
    0.41
     mädchen
    0.41
    Activations Density 0.000%

    No Known Activations