© 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. 947
    Prev
    Next
    INDEX
    Explanations

    blameless, flawless, nameless

    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
    ure
    1.96
    i
    1.91
    ن
    1.83
    ent
    1.82
    it
    1.77
    a
    1.77
    itl
    1.74
    ion
    1.73
    iation
    1.73
    ли
    1.71
    POSITIVE LOGITS
     nameless
    1.45
     AppPage
    1.43
    🤮
    1.41
     lccn
    1.39
    ან
    1.36
    ار
    1.35
    })(
    1.35
     murs
    1.34
     Pelt
    1.33
     paralyzed
    1.32
    Activations Density 0.000%

    No Known Activations