© 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. 86404
    Prev
    Next
    INDEX
    Explanations

    doubtful salesman survey area

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

    describing formal language nuance

    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
     kaikki
    0.46
     և
    0.46
     JB
    0.46
     mondiale
    0.45
    และ
    0.45
     Jaaye
    0.44
     frisk
    0.44
     Bakker
    0.43
    鷗
    0.42
     toate
    0.42
    POSITIVE LOGITS
    𝙤
    0.49
    oca
    0.47
    adesh
    0.47
    өн
    0.45
    ardır
    0.44
    ocam
    0.44
    adona
    0.44
    cade
    0.43
    riterien
    0.43
     كتاب
    0.43
    Activations Density 0.000%

    No Known Activations