© 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. 8634
    Prev
    Next
    INDEX
    Explanations

    artificially inflating numbers or size

    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
     Бі
    1.55
    ಿ
    1.53
     conos
    1.52
     emblems
    1.45
    ли
    1.44
     gateways
    1.42
    <th>
    1.34
    鎧
    1.34
     voglia
    1.32
    𝓸
    1.32
    POSITIVE LOGITS
    ่
    2.17
    أ
    1.90
    í
    1.88
    ro
    1.85
    ic
    1.80
    ер
    1.72
    ong
    1.69
     juist
    1.64
    ów
    1.55
    ره
    1.55
    Activations Density 0.002%

    No Known Activations