© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27403
    Prev
    Next
    INDEX
    Explanations

    technical and linguistic definitions

    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
     my
    -1.46
     our
    -1.43
    pullover
    -1.19
    ртқы
    -1.11
     Their
    -1.10
    ämie
    -1.09
     kesk
    -1.07
    ἵ
    -1.07
     nasceu
    -1.05
    ANNEL
    -1.04
    POSITIVE LOGITS
    deprecated
    1.20
     Obrador
    1.19
    ｾ
    1.18
     jPanel
    1.16
     médicaments
    1.16
    原始内容
    1.14
    杳
    1.14
    IZED
    1.14
     ClassNotFound
    1.13
    ceptable
    1.12
    Activations Density 0.000%

    No Known Activations