© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1491
    Prev
    Next
    INDEX
    Explanations

    Keycloak, LoRA

    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
    _
    0.79
    OLOG
    0.57
    <0xC2>
    0.57
    Y
    0.53
     ref
    0.53
      
    0.52
    IA
    0.52
    OR
    0.51
    LL
    0.51
    OLOGICAL
    0.50
    POSITIVE LOGITS
    órica
    0.73
    stätte
    0.73
    ബരി
    0.72
    ඊ
    0.69
     şə
    0.67
     entschied
    0.67
    verfahren
    0.66
    ἕ
    0.66
     つい
    0.66
    atrième
    0.66
    Activations Density 0.444%

    No Known Activations