© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 129962
    Prev
    Next
    INDEX
    Explanations

    also be / also posted / also compared

    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
     deviennent
    -1.28
     erfaring
    -1.21
     seraient
    -1.21
    恸
    -1.14
     gewel
    -1.14
    えません
    -1.14
    リエステル
    -1.12
     senaste
    -1.10
    沒有
    -1.09
    hhhhh
    -1.08
    POSITIVE LOGITS
     natürlich
    1.20
     occasionally
    1.16
    更高
    1.01
     einige
    0.98
    Gibt
    0.98
    aimerais
    0.97
     иногда
    0.96
     by
    0.96
     بعض
    0.96
     предме
    0.95
    Activations Density 0.033%

    No Known Activations