© 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. 166264
    Prev
    Next
    INDEX
    Explanations

    addition of

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

    scrutiny and examination

    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
    Temperatura
    0.43
    旄
    0.43
    щается
    0.42
     সুভাষ
    0.42
    嬙
    0.42
    Flagge
    0.41
    Whe
    0.41
    蓥
    0.41
     અથવા
    0.40
    タル
    0.39
    POSITIVE LOGITS
     dyspe
    0.50
     pans
    0.50
     quantification
    0.49
     पांड
    0.47
     stipend
    0.47
     scrutiny
    0.47
     제대로
    0.46
     novos
    0.46
     dissection
    0.46
     doubting
    0.46
    Activations Density 0.000%

    No Known Activations