© 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. 195016
    Prev
    Next
    INDEX
    Explanations

    noun or adjective + following word

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

    selling options and obligations

    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
    на
    0.54
    న
    0.54
     其
    0.52
    ول
    0.50
    ه
    0.48
    ث
    0.48
    و
    0.47
    па
    0.46
    كون
    0.46
    ف
    0.46
    POSITIVE LOGITS
    モニター
    0.49
    ಷ್ಯ
    0.47
     FSB
    0.46
     documenting
    0.46
     Rohit
    0.44
     صہیونیوں
    0.44
     EBIT
    0.43
    িয়াই
    0.43
     hamming
    0.43
    ສຸດ
    0.43
    Activations Density 0.001%

    No Known Activations