© 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. 99179
    Prev
    Next
    INDEX
    Explanations

    dates and times

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

    highlights and shared understanding

    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
    कल्
    0.48
     znajdu
    0.46
    声を
    0.43
     genitals
    0.42
    ﻮ
    0.42
    残
    0.41
    cible
    0.41
    वरून
    0.41
     formant
    0.40
     रहा
    0.40
    POSITIVE LOGITS
    歲
    0.54
    
    0.49
     নয়া
    0.47
    ပေါင်း
    0.46
    歐洲
    0.46
    amid
    0.45
     শরণার্থী
    0.44
    நோய்
    0.43
    Helvetica
    0.42
     বয়স
    0.42
    Activations Density 0.000%

    No Known Activations