© 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. 226247
    Prev
    Next
    INDEX
    Explanations

    commercial analysis victimisation

    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
     P
    0.55
     A
    0.54
     N
    0.53
     Special
    0.52
     PRIM
    0.52
     M
    0.51
    A
    0.51
     Me
    0.50
     Director
    0.50
     MATHEMAT
    0.50
    POSITIVE LOGITS
    डाउन
    0.58
    쌌
    0.57
    성이
    0.49
    下来
    0.49
    customerId
    0.49
    прия
    0.47
    탄소년단
    0.46
     hassles
    0.46
    ('')
    0.46
    성에
    0.45
    Activations Density 0.000%

    No Known Activations