© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 70342
    Prev
    Next
    INDEX
    Explanations

    database schema and data manipulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_15_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
    ('--
    1.56
    alsey
    1.54
    iania
    1.44
    nellement
    1.42
    ("--
    1.42
    补助
    1.34
    ي
    1.32
    LETE
    1.31
     declarar
    1.29
    て
    1.29
    POSITIVE LOGITS
    th
    1.89
    PK
    1.83
    pir
    1.53
    w
    1.50
     Carriage
    1.50
    FK
    1.47
    criminal
    1.46
     صحيح
    1.46
    v
    1.45
    mm
    1.44
    Activations Density 0.001%

    No Known Activations