© 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. 17-GEMMASCOPE-2-RES-16K
    7. 12575
    Prev
    Next
    INDEX
    Explanations

    about judging, private, them, magnification

    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_17_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
     والح
    1.20
     ఉన్నాయి
    1.07
    т
    1.07
    ം
    1.06
    的可能性
    1.02
    이
    1.02
    䉿
    1.00
    ′
    0.99
    𝙞
    0.98
    のは
    0.98
    POSITIVE LOGITS
    tion
    1.31
     defamation
    1.21
    tive
    1.21
    dressed
    1.20
    avait
    1.19
     hace
    1.19
    dress
    1.17
     utilizzare
    1.16
    tional
    1.15
     hacemos
    1.13
    Activations Density 0.000%

    No Known Activations