© 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
    5. 41-GEMMASCOPE-2-RES-262K
    7. 241464
    Prev
    Next
    INDEX
    Explanations

    installation or material

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obao
    0.61
    弊
    0.57
    HEAT
    0.57
    getNome
    0.55
    clare
    0.55
    clarinet
    0.55
    혐
    0.54
    နဲ့
    0.52
    Heat
    0.51
    綸
    0.51
    POSITIVE LOGITS
     dibangun
    0.65
     derivable
    0.64
     takt
    0.62
     storey
    0.61
    𝒟
    0.61
    нення
    0.60
     thema
    0.60
    туры
    0.59
     oor
    0.59
     completed
    0.59
    Activations Density 0.000%

    No Known Activations