© 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. 125393
    Prev
    Next
    INDEX
    Explanations

    keeping possession of something

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

    retain their/its/in/mode/much/full/significant

    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
    یشہ
    0.47
     オン
    0.47
    تش
    0.46
    াসী
    0.45
    َح
    0.44
     getUsersBy
    0.44
    ቑ
    0.44
    Etiam
    0.44
    ተ
    0.44
    ValidationError
    0.44
    POSITIVE LOGITS
    structural
    0.53
    utions
    0.53
    ↵
    0.52
    dirt
    0.49
    ear
    0.49
    ina
    0.48
    muc
    0.48
    prue
    0.48
    rina
    0.47
    mental
    0.47
    Activations Density 0.004%

    No Known Activations