© 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. 137377
    Prev
    Next
    INDEX
    Explanations

    no date, hope for, bush gallery

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

    descriptive phrases

    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
     mainstream
    0.47
     meist
    0.46
     mungkin
    0.45
    v
    0.45
    cki
    0.42
    pping
    0.41
    ler
    0.40
    ling
    0.40
     K
    0.39
     meestal
    0.39
    POSITIVE LOGITS
    ны
    0.54
    يح
    0.54
    મિ
    0.53
    œuvre
    0.52
    embryon
    0.52
    ራ
    0.50
    ouvoir
    0.48
    ু
    0.48
     enviar
    0.47
    હિ
    0.47
    Activations Density 0.000%

    No Known Activations