© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 17798
    Prev
    Next
    INDEX
    Explanations

    chemical, foreign languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
    ляць
    0.45
    Madrid
    0.44
    どのように
    0.43
    amnt
    0.42
     proclamation
    0.42
    谬
    0.41
    ونکہ
    0.41
     ಜನರು
    0.40
     جگہ
    0.39
     }),
    0.39
    POSITIVE LOGITS
     Polymer
    0.43
     Chemical
    0.42
     animé
    0.42
     Química
    0.41
     Polymers
    0.41
     químico
    0.41
     Políticas
    0.41
     Takah
    0.40
     enzymes
    0.40
     Kaz
    0.40
    Activations Density 0.009%

    No Known Activations