© 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. 26401
    Prev
    Next
    INDEX
    Explanations

    As you

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

    emphasis or redaction

    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
    점이
    0.48
    も含
    0.47
    कायदा
    0.46
    廪
    0.46
    난
    0.46
     unconsciously
    0.46
    점을
    0.45
    凵
    0.45
    geschoss
    0.42
    方針
    0.42
    POSITIVE LOGITS
     referenced
    0.44
     Puedes
    0.44
     которая
    0.44
     hayas
    0.43
     რომელიც
    0.42
    ൊപ്പം
    0.42
     representando
    0.42
     citado
    0.42
     antigo
    0.41
    йся
    0.41
    Activations Density 0.000%

    No Known Activations