© 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. 252018
    Prev
    Next
    INDEX
    Explanations

    free WiFi

    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
     स्वतंत्र
    0.54
    чика
    0.52
     polymerized
    0.52
     carers
    0.52
    𝘁
    0.52
     towards
    0.51
     आरमारा
    0.51
     अक्सर
    0.50
     caregivers
    0.50
     mulher
    0.50
    POSITIVE LOGITS
    ";
    0.49
    coefficient
    0.46
    “
    0.45
    《
    0.45
    「
    0.45
    »;
    0.44
    꽉
    0.43
    »).
    0.42
    ”;
    0.42
    «
    0.42
    Activations Density 0.000%

    No Known Activations