© 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. 71866
    Prev
    Next
    INDEX
    Explanations

    information queries and descriptions

    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
    without
    -1.38
    ¬
    -1.33
     particuli
    -1.30
    ›
    -1.28
    went
    -1.23
     estab
    -1.19
     vâ
    -1.18
    ï
    -1.16
    €“
    -1.16
    described
    -1.16
    POSITIVE LOGITS
     or
    2.09
     creates
    1.48
     you
    1.42
     blatantly
    1.36
     undeniably
    1.31
     supremely
    1.30
     Once
    1.28
     increases
    1.26
     generates
    1.26
     trataba
    1.25
    Activations Density 0.250%

    No Known Activations