© 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. 33111
    Prev
    Next
    INDEX
    Explanations

    dreams

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

    mimics malicious activity

    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
    之间的
    0.48
     Hypertension
    0.45
    上网
    0.45
     clockRadius
    0.45
     Subdivision
    0.43
    嫔
    0.43
    聃
    0.42
     Hãy
    0.41
    HttpSession
    0.41
     LinearLayout
    0.41
    POSITIVE LOGITS
     signalled
    0.53
    _=
    0.50
     eine
    0.48
    flag
    0.47
     wildlife
    0.45
     metoda
    0.44
    method
    0.44
     druga
    0.43
     promotes
    0.42
     handled
    0.42
    Activations Density 0.000%

    No Known Activations