© 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. 96577
    Prev
    Next
    INDEX
    Explanations

    data processing and storage

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

    organization, process, plan

    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
    }(-\
    0.57
    ト
    0.47
    柚
    0.47
    sampler
    0.47
    ンプー
    0.46
    트
    0.46
    オ
    0.45
    shoes
    0.45
    램
    0.44
    ]_
    0.44
    POSITIVE LOGITS
     Gerais
    0.60
     Leng
    0.57
     Length
    0.55
     Grundlage
    0.50
     Emilio
    0.49
     Calculations
    0.49
     Gestion
    0.48
     Unidad
    0.48
     unità
    0.48
    垲
    0.48
    Activations Density 0.000%

    No Known Activations