© 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. 161290
    Prev
    Next
    INDEX
    Explanations

    negative emotions and states

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

    mental health or states

    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
    िंग
    0.48
    ुलर
    0.46
    öse
    0.45
    нала
    0.44
    nesium
    0.43
    feet
    0.43
    ō
    0.43
    이트
    0.43
    ना
    0.42
    regor
    0.42
    POSITIVE LOGITS
     anorexia
    0.56
     antidepressant
    0.55
     melancholy
    0.55
     antidepress
    0.54
     depressed
    0.51
     adaptable
    0.51
     slower
    0.50
     depres
    0.50
     sabi
    0.50
     seduced
    0.50
    Activations Density 0.000%

    No Known Activations