© 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. 175442
    Prev
    Next
    INDEX
    Explanations

    status, completion, or conditions

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

    philosophical existential discussion

    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
    Ads
    0.50
    د
    0.50
    に基づく
    0.46
     dis
    0.44
     deth
    0.43
     compose
    0.42
    anger
    0.41
    compose
    0.41
     bisher
    0.41
     curate
    0.40
    POSITIVE LOGITS
    берг
    0.46
    ృష్టి
    0.46
    𝔹
    0.46
     riusc
    0.45
     पिया
    0.45
     ٹینس
    0.45
    峦
    0.44
     తాగ
    0.43
    טים
    0.43
    varepsilon
    0.43
    Activations Density 0.001%

    No Known Activations