© 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. 31-GEMMASCOPE-2-RES-262K
    7. 8517
    Prev
    Next
    INDEX
    Explanations

    arithmetic word problems

    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_31_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
    िकेटेड
    0.43
    ）・
    0.41
     cinematographer
    0.41
     relevancia
    0.40
    রামর্শ
    0.40
    اویز
    0.40
     procesamiento
    0.39
    叧
    0.39
    ாய்ச்சி
    0.39
    क्टूबर
    0.37
    POSITIVE LOGITS
     underlying
    0.51
     hidden
    0.48
     must
    0.48
     riddle
    0.45
     원래
    0.43
    ?
    0.41
     unknown
    0.40
     deduce
    0.40
    原来
    0.40
    !
    0.40
    Activations Density 0.099%

    No Known Activations