© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 4214
    Prev
    Next
    INDEX
    Explanations

    tame little dog

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
     médecins
    1.25
     callSettings
    1.16
     olympiques
    1.15
     malades
    1.11
    大学
    1.08
    :'],
    1.07
     titers
    1.06
    的大
    1.04
    servicetime
    1.04
    '`,
    1.02
    POSITIVE LOGITS
    l
    2.27
    d
    1.99
    r
    1.87
    al
    1.84
    el
    1.83
    a
    1.79
    ar
    1.76
    m
    1.74
    er
    1.72
    e
    1.72
    Activations Density 2.178%

    No Known Activations