© 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. 121304
    Prev
    Next
    INDEX
    Explanations

    doubtless, undoubtedly, certainly

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

    conjunctions or contrast words

    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
    และการ
    0.57
     तसेच
    0.51
    You
    0.48
    Anda
    0.48
     ਅਤੇ
    0.47
     आणि
    0.47
     અને
    0.45
    Í
    0.44
     மற்றும்
    0.44
    และ
    0.44
    POSITIVE LOGITS
     doubtless
    0.52
     নিঃসন্দেহে
    0.52
    るのは
    0.50
     ngunit
    0.50
     වන්නේ
    0.50
     certamente
    0.49
     undoubtedly
    0.49
     dunque
    0.49
     unquestionably
    0.48
     evidentemente
    0.47
    Activations Density 0.025%

    No Known Activations