© 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. 60530
    Prev
    Next
    INDEX
    Explanations

    castle or more

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

    concepts and media analysis

    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
    ћи
    0.45
    τής
    0.45
    that
    0.44
    हाई
    0.44
    挤
    0.44
    readonly
    0.43
     sneak
    0.42
    ilor
    0.41
    මට
    0.41
     setup
    0.41
    POSITIVE LOGITS
    城堡
    0.47
     城
    0.43
    堡
    0.43
     Autoren
    0.43
    }={\
    0.42
    ageddon
    0.42
     南
    0.42
    رب
    0.42
    晟
    0.42
    ichtet
    0.42
    Activations Density 0.000%

    No Known Activations