© 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. 135705
    Prev
    Next
    INDEX
    Explanations

    events or conditions

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

    attacker controls

    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
    å
    0.45
    の内
    0.44
    続
    0.44
    purpose
    0.43
    verte
    0.41
    Figure
    0.41
    modal
    0.41
    gage
    0.39
    猕
    0.39
    Monty
    0.39
    POSITIVE LOGITS
    DrvGPIO
    0.49
    SpriteCollision
    0.47
    _{+}
    0.46
    ⱪ
    0.46
     ヴィンテージ
    0.45
    जिस्ट
    0.45
    }_{\
    0.44
    ड्रन
    0.44
    }_{+}
    0.44
    buenas
    0.44
    Activations Density 0.002%

    No Known Activations