© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8271
    Prev
    Next
    INDEX
    Explanations

    existence and quantity in many languages

    np_acts-logits-general · gemini-2.5-flash-lite

    LM Studio

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_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
    }^{-}$
    0.45
    autre
    0.43
    গকে
    0.43
    ående
    0.40
     disrupts
    0.40
     positioning
    0.39
    }^{*}$,
    0.39
     تاسو
    0.38
     সংসারের
    0.38
     점에서
    0.38
    POSITIVE LOGITS
    Hers
    0.49
    많
    0.48
    망
    0.48
     terdapat
    0.47
     생긴
    0.46
     நிறைய
    0.46
    最多的
    0.46
     많
    0.45
     criado
    0.45
    Plenty
    0.45
    Activations Density 0.001%

    No Known Activations