© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 3429
    Prev
    Next
    INDEX
    Explanations

    thinking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    coelastic
    0.79
    排出
    0.77
    ^{+}\
    0.76
    ^{-}\
    0.73
    iphenyl
    0.73
    bibitem
    0.71
     schließen
    0.70
     ヨコハマ
    0.68
    են
    0.68
    Cursors
    0.67
    POSITIVE LOGITS
     CNS
    0.81
     age
    0.80
     NYC
    0.79
     VoIP
    0.79
     Age
    0.77
     Info
    0.76
     —
    0.73
     Nature
    0.71
     ABC
    0.71
     NOC
    0.71
    Activations Density 0.033%

    No Known Activations