© 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. 8930
    Prev
    Next
    INDEX
    Explanations

    awareness of self

    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
    مار
    0.49
    KIA
    0.47
    dari
    0.46
    ,--
    0.46
    тни
    0.45
    -
    0.45
    켐
    0.45
    YT
    0.45
    AKI
    0.45
    NORM
    0.43
    POSITIVE LOGITS
     généralement
    0.44
    maximizing
    0.43
    pleClass
    0.43
    大概
    0.43
    onin
    0.42
     maximizing
    0.41
     सर्वश्रेष्ठ
    0.41
    ges
    0.41
     झू
    0.41
     शॉर्ट
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.