© 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. 164150
    Prev
    Next
    INDEX
    Explanations

    any navigation

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

    prevent damage, access systems, sneak past

    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
    GM
    0.48
    Ukraine
    0.46
    ใน
    0.46
    Ü
    0.45
    杨
    0.45
    BLACK
    0.44
    त
    0.44
    ັດ
    0.43
     amazingly
    0.43
    Ukrainian
    0.43
    POSITIVE LOGITS
    atschapp
    0.50
     Decentral
    0.48
     Innoc
    0.48
    راءة
    0.47
    zicht
    0.46
     الاجتماعي
    0.46
     !==
    0.46
     Config
    0.46
    󠁳
    0.46
     వ్యవస్థ
    0.46
    Activations Density 0.000%

    No Known Activations