© 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. 184417
    Prev
    Next
    INDEX
    Explanations

    free daily updates

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

    Translate or equations

    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
     endereço
    0.47
    顶部
    0.46
     molestias
    0.46
     эко
    0.45
    禊
    0.45
     comunic
    0.44
     শব্দটি
    0.44
     والی
    0.43
     άλλ
    0.43
     puse
    0.43
    POSITIVE LOGITS
    mappings
    0.44
    (&
    0.44
    whereas
    0.43
    ($
    0.42
    foreground
    0.42
     అర్జు
    0.42
    í
    0.42
    techniques
    0.41
    θαν
    0.41
    }(\
    0.40
    Activations Density 0.000%

    No Known Activations