© 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. 38434
    Prev
    Next
    INDEX
    Explanations

    books and novels

    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
    ּוֹ
    -1.22
    PUESTA
    -1.20
    객체
    -1.19
     modeli
    -1.16
    }>{
    -1.16
    onekana
    -1.14
    wezig
    -1.09
    ﻷ
    -1.09
    wanne
    -1.08
     fotografi
    -1.07
    POSITIVE LOGITS
     chré
    1.16
     verknüp
    1.11
    qquad
    1.07
     掃除
    1.05
    ствую
    1.05
    dropna
    1.04
     Readers
    1.04
     литератур
    1.03
    lateinit
    1.02
     ancaman
    1.02
    Activations Density 0.063%

    No Known Activations