© 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. 155182
    Prev
    Next
    INDEX
    Explanations

    environmental and technical regulations

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

    Controlling Behavior, impacts decision

    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
    িন
    0.48
    ैन
    0.48
     response
    0.44
     stamp
    0.44
    slag
    0.42
    Regist
    0.42
    产
    0.41
     frenzy
    0.40
    ཤ
    0.39
     mask
    0.39
    POSITIVE LOGITS
     inférieures
    0.62
    NotBlank
    0.59
    avgsalary
    0.57
     ovipares
    0.56
     educativas
    0.54
    you
    0.50
     personable
    0.50
     chercheurs
    0.50
    礁
    0.50
     algéb
    0.50
    Activations Density 0.000%

    No Known Activations