© 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. 25546
    Prev
    Next
    INDEX
    Explanations

    credit score

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

    score, height, constraint, manager, intake

    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
    |^{\
    0.43
    Ý
    0.41
    ttu
    0.41
    _
    0.40
    RI
    0.40
    Ó
    0.40
    Osc
    0.38
    "/"
    0.38
    UTF
    0.38
    }\
    0.38
    POSITIVE LOGITS
     sechs
    0.50
     быстрее
    0.50
     weitere
    0.49
     zehn
    0.49
     რომელიც
    0.48
     langfrist
    0.47
     fünf
    0.47
     drei
    0.47
     ይህም
    0.46
     வேகமாக
    0.46
    Activations Density 0.002%

    No Known Activations