© 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. 120551
    Prev
    Next
    INDEX
    Explanations

    university and colleges

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

    self-description characteristics

    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
     ನಿಮ್ಮ
    0.48
    傆
    0.46
     previa
    0.46
    ్వర
    0.46
     ਤੁਹਾ
    0.46
     ਆਪਣ
    0.45
    minim
    0.44
    íd
    0.43
     기존
    0.43
    会让
    0.43
    POSITIVE LOGITS
    université
    0.46
     académ
    0.42
    鎴
    0.42
    ष्णु
    0.41
    ologues
    0.40
     glories
    0.40
     university
    0.40
     solchen
    0.39
     ذلك
    0.39
     saint
    0.39
    Activations Density 0.000%

    No Known Activations