© 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. 40-GEMMASCOPE-2-RES-262K
    7. 167673
    Prev
    Next
    INDEX
    Explanations

    numpy array operations

    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_40_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
    movement
    0.45
    prom
    0.43
    7
    0.42
    ur
    0.42
     Movement
    0.42
    R
    0.42
     movement
    0.41
    g
    0.41
    MOVEMENT
    0.40
    Caso
    0.40
    POSITIVE LOGITS
    slideDuplicate
    0.46
    ftone
    0.45
    ዎች
    0.43
    ቶች
    0.42
     համ
    0.42
    ከት
    0.42
     održ
    0.41
    行走
    0.41
    🤴
    0.41
    涣
    0.40
    Activations Density 0.004%

    No Known Activations