© 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. 5618
    Prev
    Next
    INDEX
    Explanations

    tips and advice

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

    non-english text

    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
     praxis
    0.41
     initiator
    0.41
     anbef
    0.41
     onboarding
    0.41
    }:
    0.39
     raison
    0.39
     prosedur
    0.39
     progen
    0.39
     palvel
    0.39
     candidature
    0.39
    POSITIVE LOGITS
    磧
    0.48
    韪
    0.48
     Якщо
    0.46
    <unused2148>
    0.45
     Aunque
    0.44
     које
    0.44
    虽然
    0.44
    إذا
    0.44
    Якщо
    0.43
    τική
    0.43
    Activations Density 0.245%

    No Known Activations