© 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. 31-GEMMASCOPE-2-RES-262K
    7. 60836
    Prev
    Next
    INDEX
    Explanations

    terms and conditions

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

    justifies detailing action is fuels classical ideal crucial to subject matter share via formula :

    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_31_width_262k_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
     قالت
    0.47
    परेट
    0.47
    izzo
    0.46
     เจอ
    0.46
    擰
    0.46
    比如說
    0.44
    仯
    0.44
     જણાવ
    0.44
    獧
    0.44
    uales
    0.43
    POSITIVE LOGITS
     firearm
    0.46
     microbiome
    0.45
     nahezu
    0.43
     firearms
    0.40
     সমাধি
    0.40
     admired
    0.39
     collector
    0.38
     flowed
    0.37
     ấm
    0.37
     centuries
    0.36
    Activations Density 0.000%

    No Known Activations