© 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. 32031
    Prev
    Next
    INDEX
    Explanations

    felony and robbery

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

    cultural perspective or lineage

    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
     nở
    0.48
    كين
    0.47
    ية
    0.46
    이를
    0.44
    قية
    0.44
     dusted
    0.44
     soared
    0.43
    ک
    0.43
    ак
    0.43
    파
    0.42
    POSITIVE LOGITS
    0.56
     felony
    0.52
     cDNA
    0.50
     sponsorship
    0.48
     জাহান
    0.46
     endorsement
    0.46
     evolutionary
    0.45
    Limited
    0.45
     gruesome
    0.45
     adjudication
    0.44
    Activations Density 0.000%

    No Known Activations