© 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. 179609
    Prev
    Next
    INDEX
    Explanations

    psyche, psychology, psychiatric

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

    psychology, psi, psychedelic, psychonauts

    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
     Policing
    0.48
     sosial
    0.46
    ¹.
    0.45
    Emotional
    0.44
    लीट
    0.43
     Parte
    0.43
    KPI
    0.43
    social
    0.43
     policing
    0.43
     sitio
    0.42
    POSITIVE LOGITS
     Pseudo
    0.48
    mathscr
    0.44
    がか
    0.44
     Pseud
    0.44
    あり
    0.43
    滯
    0.43
    がつ
    0.41
    伪
    0.40
     Macintosh
    0.40
    Methylsulfanyl
    0.40
    Activations Density 0.004%

    No Known Activations