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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1692
    Prev
    Next
    INDEX
    Explanations

    dialogue after saying

    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_12_width_65k_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
    сро
    2.28
    Y
    2.20
    ungannya
    2.13
    astic
    2.05
    ouncement
    2.04
    Ｄ
    2.04
    (=
    2.01
    сле
    1.99
    (&
    1.97
    yp
    1.97
    POSITIVE LOGITS
    rinsic
    2.18
     makeSound
    1.86
     nameless
    1.78
    <unused505>
    1.70
    readonly
    1.67
    Diffuse
    1.65
     încep
    1.64
     materias
    1.64
    <unused1750>
    1.64
     инфра
    1.62
    Activations Density 0.529%

    No Known Activations