© 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-65K
    7. 3162
    Prev
    Next
    INDEX
    Explanations

    positive integers 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_65k_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
     efficacious
    0.99
     proximate
    0.86
     inputted
    0.85
     peculiarly
    0.84
     ಅಂತ
    0.82
     classed
    0.81
     accorded
    0.79
    <unused2100>
    0.79
     discerned
    0.79
     sizeable
    0.78
    POSITIVE LOGITS
     ​​
    1.09
     XNUMX
    1.05
    NUMX
    0.88
     և
    0.87
     ​​​​
    0.78
    Ს
    0.78
     गले
    0.70
    忘れ
    0.70
    nagar
    0.69
    Ე
    0.67
    Activations Density 0.059%

    No Known Activations