© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33543
    Prev
    Next
    INDEX
    Explanations

    bombs and explosions

    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
    ot
    -1.24
    /*
    -1.22
    vaila
    -1.21
    re
    -1.20
     abomination
    -1.19
    ra
    -1.18
     prácti
    -1.17
    <i>
    -1.17
     awakeFromNib
    -1.16
    .”
    -1.16
    POSITIVE LOGITS
     Они
    1.38
    ватися
    1.37
    
    1.27
     esquer
    1.26
     انداز
    1.25
    ัติ
    1.24
     explosion
    1.22
     maleta
    1.20
    衚
    1.19
    rums
    1.18
    Activations Density 0.043%

    No Known Activations