© 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. 159758
    Prev
    Next
    INDEX
    Explanations

    Silicon Valley, olive oil, comic, waterfall, Gervais

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

    relaxing, recognizing, or watching

    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
     logits
    0.44
    igated
    0.39
    饽
    0.39
    öhn
    0.38
    ევს
    0.38
    ionicons
    0.38
    fontWeight
    0.37
     milhões
    0.37
    etli
    0.37
    ొప్ప
    0.37
    POSITIVE LOGITS
     그러니까
    0.55
    に関しては
    0.50
     analyse
    0.50
    zone
    0.49
     usurp
    0.49
     deny
    0.48
    至於
    0.47
    㕵
    0.47
     अन्तर्गत
    0.47
    伷
    0.47
    Activations Density 0.000%

    No Known Activations