© 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. 242247
    Prev
    Next
    INDEX
    Explanations

    critical thinking

    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
     divorced
    0.52
     responded
    0.50
     gara
    0.50
     whispers
    0.50
    …
    0.50
     respond
    0.49
    .,
    0.49
     zare
    0.48
     divor
    0.48
    ”.
    0.48
    POSITIVE LOGITS
    稒
    0.49
    reasonably
    0.49
    亽
    0.48
    剻
    0.48
    aises
    0.46
    urring
    0.46
    嘍
    0.46
    牰
    0.46
    逅
    0.46
    atória
    0.46
    Activations Density 0.000%

    No Known Activations