© 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. 90585
    Prev
    Next
    INDEX
    Explanations

    market results, even though, footage using

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

    quotes, desires, trends, critical

    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
    lade
    0.49
    मोह
    0.48
    лян
    0.48
     क्लियर
    0.47
     Estudios
    0.47
    acjach
    0.46
    abond
    0.46
    奥
    0.46
    तंत्र
    0.45
     नियमित
    0.45
    POSITIVE LOGITS
     konuştu
    0.46
     satiety
    0.44
     Randy
    0.43
     mercantile
    0.43
     grassy
    0.42
     drank
    0.42
     radially
    0.42
     thatch
    0.42
     predominate
    0.42
     windy
    0.41
    Activations Density 0.000%

    No Known Activations