© 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. 51271
    Prev
    Next
    INDEX
    Explanations

    actions or states of being

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

    shared experience fantasy

    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
    ⬝
    0.49
    تھی
    0.46
     αντί
    0.44
    ρν
    0.44
    ιον
    0.43
     vinculado
    0.42
    綃
    0.42
     sculpture
    0.41
     Marlon
    0.41
    僮
    0.41
    POSITIVE LOGITS
    ِّف
    0.49
    kens
    0.46
     جع
    0.46
     نست
    0.46
     தவ
    0.46
     非
    0.45
    omm
    0.45
    fhir
    0.45
    }}.
    0.44
    வ
    0.44
    Activations Density 0.000%

    No Known Activations