© 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. 19440
    Prev
    Next
    INDEX
    Explanations

    describing processes and states

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

    gaslighting and reality distortion

    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
     vésicules
    0.49
    фа
    0.48
    она
    0.45
     л
    0.45
    уна
    0.44
    武器
    0.44
    筋肉
    0.43
     generaciones
    0.43
    デバイス
    0.43
     chieft
    0.42
    POSITIVE LOGITS
     Techniques
    0.49
     سایر
    0.48
     Worked
    0.47
    澀
    0.45
     "}
    0.44
     Shown
    0.44
    Ûn
    0.44
     তালিকায়
    0.43
     것처럼
    0.43
     Causes
    0.42
    Activations Density 0.000%

    No Known Activations