© 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. 25912
    Prev
    Next
    INDEX
    Explanations

    other languages

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

    different or other options

    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
     mandatory
    0.39
     motorcycle
    0.39
     cadet
    0.38
     adventurer
    0.38
     GSM
    0.38
     GPL
    0.38
     Greyhound
    0.38
    旛
    0.38
     hostel
    0.38
     dropping
    0.38
    POSITIVE LOGITS
     anderen
    0.47
    ilem
    0.45
     अन्यथा
    0.44
    amless
    0.44
    sonsten
    0.44
     અન્ય
    0.43
     others
    0.42
    others
    0.41
     інших
    0.41
     অন্যরা
    0.41
    Activations Density 0.000%

    No Known Activations