© 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. 172843
    Prev
    Next
    INDEX
    Explanations

    components and alliances

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

    entities and concepts

    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
     увеличить
    0.47
     arkadaş
    0.46
    increased
    0.45
     aumenta
    0.45
    ेंटिस
    0.45
     increase
    0.44
    曛
    0.44
     অভাবে
    0.44
     vijj
    0.44
     cenderung
    0.44
    POSITIVE LOGITS
     OSI
    0.44
    統
    0.43
    都有
    0.42
    思想
    0.41
     geopol
    0.40
     ontological
    0.40
     coord
    0.39
     nuanced
    0.39
    synt
    0.39
     SIST
    0.39
    Activations Density 0.000%

    No Known Activations