© 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. 117691
    Prev
    Next
    INDEX
    Explanations

    collateral or debt

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

    intent classification, extraction, NLP, rights

    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
    ø
    0.49
    теру
    0.48
     incarnations
    0.48
    ריה
    0.47
    0.45
    鉭
    0.44
    谕
    0.44
    ింది
    0.44
    endance
    0.44
    จะ
    0.43
    POSITIVE LOGITS
    caso
    0.49
     энерго
    0.49
     subtração
    0.49
    unfair
    0.48
    DA
    0.46
     বিদেশী
    0.46
    chatbot
    0.46
    ㎥
    0.46
     unfair
    0.45
    sav
    0.45
    Activations Density 0.001%

    No Known Activations