© 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. 2375
    Prev
    Next
    INDEX
    Explanations

    years and numbers

    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
    6
    0.62
    5
    0.59
    Six
    0.55
    élim
    0.54
    8
    0.54
    Nine
    0.53
    7
    0.52
     அலுவலக
    0.52
    9
    0.51
     бе
    0.51
    POSITIVE LOGITS
    PLASMA
    0.64
    hæng
    0.62
    対訳
    0.60
     Augmented
    0.60
     bowtie
    0.59
     Craft
    0.58
     breaches
    0.58
    ぐるみ
    0.57
    िएगा
    0.57
     SOAP
    0.57
    Activations Density 0.125%

    No Known Activations