© 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. 46167
    Prev
    Next
    INDEX
    Explanations

    your plan

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

    HUGE benefits

    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
     nebude
    0.52
     cliffs
    0.44
     ;-)
    0.43
    Nicht
    0.42
    च्युअल
    0.42
    COMANDA
    0.42
     salads
    0.42
     પૂર્ણ
    0.42
    savefig
    0.41
    벚
    0.41
    POSITIVE LOGITS
     oppressive
    0.46
    声道
    0.42
     repug
    0.41
     उसने
    0.40
     लड़के
    0.40
     તેને
    0.39
     repressive
    0.38
     назвал
    0.37
     damning
    0.37
    撼
    0.37
    Activations Density 0.000%

    No Known Activations