© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 1447
    Prev
    Next
    INDEX
    Explanations

    unparalleled or unprecedented

    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
    ные
    1.33
    }
    1.18
    ]
    1.12
    ار
    1.05
    ocomplete
    1.05
    то
    1.04
    epsilon
    1.02
    не
    1.02
    _
    1.02
    ctive
    1.00
    POSITIVE LOGITS
    alarını
    1.36
    К
    1.21
    एम
    1.17
    У
    1.17
    아
    1.17
    lara
    1.16
    ørt
    1.16
    Archae
    1.16
    alarının
    1.11
     biết
    1.10
    Activations Density 0.043%

    No Known Activations