© 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. 107660
    Prev
    Next
    INDEX
    Explanations

    revision, pdf, after sales, toggle, resource, parents

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

    Vibe Check and Difficulty

    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
     kasus
    0.38
    ೨
    0.35
    ið
    0.35
    ë
    0.35
     மேலும்
    0.34
     alguien
    0.34
     Дон
    0.34
    
    0.34
    ፡፡
    0.34
    ية
    0.34
    POSITIVE LOGITS
    CrossOrigin
    0.31
     sawtooth
    0.31
    Parameteri
    0.30
     compensates
    0.30
    ﹟
    0.29
    ButtonBar
    0.29
     rectify
    0.29
     但
    0.29
    )=>{
    0.29
     soundtracks
    0.29
    Activations Density 0.053%

    No Known Activations