© 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. 115487
    Prev
    Next
    INDEX
    Explanations

    palindromes, attempt, nightmare

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

    words following specific terms

    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
     comunit
    0.48
    supportsFocus
    0.45
    ácter
    0.44
    vercel
    0.44
     把
    0.44
     caracter
    0.43
    FAO
    0.42
     caratter
    0.42
    CCO
    0.42
    cknowledg
    0.42
    POSITIVE LOGITS
    めた
    0.50
    వంత
    0.47
     Hitt
    0.46
    chill
    0.46
    癇
    0.45
     acceptable
    0.44
    めて
    0.44
    цах
    0.44
    すぎて
    0.44
    拡張
    0.44
    Activations Density 0.000%

    No Known Activations