© 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. 219961
    Prev
    Next
    INDEX
    Explanations

    deal possible

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

    payments, care, legal obligations

    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
    ')
    0.51
    ']].
    0.51
    ')).
    0.50
    Proble
    0.50
    '}}
    0.49
    '}).
    0.48
     الول
    0.48
    ائها
    0.48
    閱
    0.48
    TOOL
    0.47
    POSITIVE LOGITS
     coax
    0.57
     Khmer
    0.51
    ך
    0.49
     supports
    0.48
     Lian
    0.48
     coaxial
    0.47
     adults
    0.47
     Buddhists
    0.46
     smudge
    0.46
     chopsticks
    0.46
    Activations Density 0.000%

    No Known Activations