© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 33603
    Prev
    Next
    INDEX
    Explanations

    tsunami and CDC warnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_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
    ر
    1.56
    nement
    1.22
    ről
    1.22
    l
    1.19
    و
    1.18
    of
    1.15
    مر
    1.13
    ные
    1.13
    ي
    1.13
    ni
    1.10
    POSITIVE LOGITS
     CDC
    1.15
     jeu
    1.09
     on
    1.01
     ODI
    0.96
    ၿ
    0.96
     RoHS
    0.95
     gioco
    0.91
     AdWords
    0.91
     CII
    0.90
     corpi
    0.90
    Activations Density 0.001%

    No Known Activations