© 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. 3674
    Prev
    Next
    INDEX
    Explanations

    listing multiple items

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

    both

    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
     implique
    0.35
    匏
    0.35
     ಮತ್ತ
    0.34
    ிலும்
    0.34
    فل
    0.33
    पी
    0.33
    鄴
    0.33
    藥
    0.33
    謊
    0.33
    錡
    0.33
    POSITIVE LOGITS
    それぞれ
    0.42
     entrambi
    0.41
     begge
    0.40
     ஆகியவற்ற
    0.40
     beide
    0.40
     উভয়
    0.39
     എന്നിവ
    0.38
     ஆகிய
    0.38
     উভয়
    0.38
     respectively
    0.38
    Activations Density 0.072%

    No Known Activations