© 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. 95172
    Prev
    Next
    INDEX
    Explanations

    varies depending, options in, absorption of

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

    contextual understanding and betrayal

    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
    拼
    0.46
     unethical
    0.46
    expanding
    0.45
     نفرت
    0.45
    beschreibung
    0.44
    Become
    0.44
    become
    0.44
    bodies
    0.43
    美国
    0.43
    heiten
    0.42
    POSITIVE LOGITS
     Năm
    0.50
     Jh
    0.48
     Nhưng
    0.48
     Spa
    0.48
     n
    0.47
     પરંતુ
    0.47
     Salat
    0.47
     Pape
    0.47
     Drain
    0.46
    }_{+}
    0.46
    Activations Density 0.000%

    No Known Activations