© 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. 128778
    Prev
    Next
    INDEX
    Explanations

    legal claims, foils, stunning, review, talking, God

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

    generate harmful content

    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
     Subdistrict
    0.46
    这也
    0.45
    这
    0.42
     podle
    0.42
     zog
    0.42
    ين
    0.42
     cosidd
    0.41
    這
    0.41
     Jr
    0.41
     Billy
    0.41
    POSITIVE LOGITS
     बलात्कार
    0.49
     necessário
    0.48
    јединачна
    0.45
    foils
    0.45
    preco
    0.44
     अत्याचार
    0.43
    oppositions
    0.43
    installer
    0.43
     overthrow
    0.42
     alternativa
    0.41
    Activations Density 0.001%

    No Known Activations