© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 3866
    Prev
    Next
    INDEX
    Explanations

    crucial to/for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_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
     assass
    1.42
    e
    1.31
     annihil
    1.26
     sheer
    1.24
     dint
    1.23
     Bla
    1.20
     niets
    1.19
     आम
    1.16
     extrad
    1.16
     Maggiore
    1.16
    POSITIVE LOGITS
    ता
    1.38
    že
    1.38
    ă
    1.38
    íf
    1.36
    ó
    1.36
    ifies
    1.34
    तमंद
    1.34
    é
    1.31
    ן
    1.31
    ۀ
    1.31
    Activations Density 0.376%

    No Known Activations