© 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. 31-GEMMASCOPE-2-RES-65K
    7. 61456
    Prev
    Next
    INDEX
    Explanations

    proper nouns and identifiers

    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_31_width_65k_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
     mercantil
    0.52
     verursacht
    0.50
     unreasonable
    0.48
    ilitary
    0.46
     edificio
    0.46
     filosofía
    0.46
    🚍
    0.46
    netic
    0.45
     eficiente
    0.45
     relacionado
    0.45
    POSITIVE LOGITS
     M
    0.46
     أحمد
    0.43
    მოს
    0.42
     Participant
    0.41
     Mas
    0.40
     P
    0.40
     Dancer
    0.39
     V
    0.38
     Mant
    0.38
     Na
    0.38
    Activations Density 0.014%

    No Known Activations