© 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. 60516
    Prev
    Next
    INDEX
    Explanations

    agent and directory

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

    recursive utility

    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
    }))
    0.52
     vibrates
    0.46
    MAN
    0.45
     swirls
    0.44
     ries
    0.43
    enziale
    0.43
     stare
    0.42
     obsess
    0.42
     ഞാൻ
    0.42
    }...
    0.41
    POSITIVE LOGITS
    вало
    0.50
     forerunner
    0.49
     безопасности
    0.46
    导弹
    0.45
    ant
    0.45
    ター
    0.45
     कार्रवाई
    0.45
    違い
    0.44
    になり
    0.44
    ボール
    0.44
    Activations Density 0.000%

    No Known Activations