© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 168926
    Prev
    Next
    INDEX
    Explanations

    understanding uncertainty and justification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ret
    0.46
    RG
    0.44
    rg
    0.44
     respostas
    0.42
     respuesta
    0.40
    права
    0.39
     obtener
    0.38
    /-/
    0.38
    strij
    0.38
    ibil
    0.37
    POSITIVE LOGITS
     dirty
    0.42
     छात्र
    0.40
     étudiant
    0.40
     Australians
    0.40
     zvlá
    0.39
    Austral
    0.38
     employing
    0.38
     Groß
    0.38
    धव
    0.37
     anonymous
    0.37
    Activations Density 0.001%

    No Known Activations