© 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. 158546
    Prev
    Next
    INDEX
    Explanations

    Globe, Houses, 4 wherein, free-, cartridge, Holdings, latter scenario

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

    without consent or choice

    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
     денег
    0.50
     алкого
    0.49
     инвали
    0.46
    тся
    0.46
     אי
    0.46
     прошлого
    0.45
     �
    0.45
     गिर
    0.44
    .'/
    0.44
     ï
    0.44
    POSITIVE LOGITS
    suite
    0.47
    راتيج
    0.47
     Hearth
    0.46
    ચારી
    0.44
     musia
    0.43
    su
    0.43
    sm
    0.43
     nový
    0.42
    si
    0.41
     baseline
    0.41
    Activations Density 0.001%

    No Known Activations