© 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. 195572
    Prev
    Next
    INDEX
    Explanations

    lists after quantifiers

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

    API access, marketing teams, SQL injection

    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
     amending
    0.45
    \{-\
    0.45
    ጹ
    0.43
     সভাপত
    0.41
    愆
    0.41
     modulating
    0.41
     गिरने
    0.41
     BIB
    0.40
     pourront
    0.40
     repug
    0.40
    POSITIVE LOGITS
     pelo
    0.54
    y
    0.53
     போலீ
    0.53
    ómo
    0.52
     término
    0.52
    ot
    0.51
    ov
    0.50
     godina
    0.49
     prova
    0.49
     自
    0.49
    Activations Density 0.000%

    No Known Activations