© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 165062
    Prev
    Next
    INDEX
    Explanations

    harming the environment

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

    what

    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
     அல்லாஹ்வின்
    0.57
    사의
    0.50
     alienated
    0.49
    <unused40>
    0.48
     ސ
    0.48
    strdup
    0.48
     phosphorylated
    0.47
     تعالی
    0.47
    default
    0.46
     বরাদ্দ
    0.46
    POSITIVE LOGITS
    re
    0.53
    I
    0.52
    Do
    0.51
    wang
    0.50
    usi
    0.48
    ß
    0.47
    jak
    0.46
    We
    0.46
    ow
    0.46
    oric
    0.46
    Activations Density 0.000%

    No Known Activations