© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 70822
    Prev
    Next
    INDEX
    Explanations

    LGPL licenses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    -2.20
    ांकि
    -2.16
     replete
    -2.03
    erintah
    -2.02
     стоковая
    -1.98
    瑨
    -1.98
     Agronomy
    -1.89
    isations
    -1.88
    ཋ
    -1.88
    鋮
    -1.85
    POSITIVE LOGITS
    ではまた
    2.53
    𓍊
    2.31
    ?”
    2.28
    ではでは
    2.20
    ｘ
    2.14
    ﻒ
    2.11
     sué
    2.06
     of
    2.06
     kimdir
    2.05
    橚
    2.05
    Activations Density 0.004%

    No Known Activations