© 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. 88226
    Prev
    Next
    INDEX
    Explanations

    problem with these members

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

    not the thing itself

    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
    습니다
    0.51
    ني
    0.49
     느껴
    0.46
    nueva
    0.46
     ப
    0.44
     контек
    0.43
    appropriate
    0.42
    ச்சூழ
    0.42
     அளவிற்கு
    0.41
    вера
    0.41
    POSITIVE LOGITS
     popped
    0.42
     biasanya
    0.42
     brushless
    0.42
     cursory
    0.41
     apnea
    0.41
     disqualified
    0.40
     athletes
    0.40
     establishments
    0.40
     他
    0.40
     langu
    0.39
    Activations Density 0.003%

    No Known Activations