© 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. 84066
    Prev
    Next
    INDEX
    Explanations

    overridden by interests or freedoms

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

    used to cause harm

    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
     Difficult
    0.48
    ר
    0.47
     Situ
    0.46
    रल
    0.46
     。
    0.45
    r
    0.45
    ra
    0.44
     Patience
    0.44
    la
    0.43
    tense
    0.43
    POSITIVE LOGITS
     данном
    0.44
    獃
    0.41
     সন্দ
    0.40
     publisher
    0.40
     leveraged
    0.38
     conclusively
    0.38
    無料で
    0.38
     данни
    0.38
    ື່
    0.38
    '<
    0.38
    Activations Density 0.001%

    No Known Activations