© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9419
    Prev
    Next
    INDEX
    Explanations

    disk and partition management

    np_acts-logits-general · gemini-2.5-flash-lite

    comment delimiters // # -- /*

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jantar
    0.43
     Аб
    0.42
     Moreno
    0.40
    📶
    0.40
     நன்க
    0.39
     ресто
    0.38
     tráfico
    0.38
     тар
    0.38
     }*/
    0.37
     পান
    0.37
    POSITIVE LOGITS
     xs
    0.40
    막
    0.40
    //
    0.39
    idopsis
    0.38
     Vys
    0.38
     propagates
    0.37
    ګه
    0.37
     eff
    0.36
    ाय
    0.36
    SANIT
    0.36
    Activations Density 0.004%

    No Known Activations