© 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. 31102
    Prev
    Next
    INDEX
    Explanations

    probability and likelihood

    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
     ይታ
    0.50
    蒿
    0.49
    iąz
    0.48
     기준
    0.46
     몸
    0.45
    绷
    0.45
     επέ
    0.45
    ㄼ
    0.45
    란
    0.44
     замі
    0.43
    POSITIVE LOGITS
     probabilities
    1.46
     probability
    1.42
     вероятность
    1.30
     probabilidad
    1.27
    probability
    1.25
     probabilidades
    1.20
     Probability
    1.17
    概率
    1.11
    Probability
    1.10
    probabilities
    1.09
    Activations Density 0.315%

    No Known Activations