© 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. 15077
    Prev
    Next
    INDEX
    Explanations

    digits, bit, halves

    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
     جوړونکو
    0.49
     déjeuner
    0.44
     नागरिकों
    0.44
     informée
    0.43
    Plaintiffs
    0.42
    దారు
    0.42
    噂
    0.41
    Ϥ
    0.41
     uczest
    0.40
     discredit
    0.39
    POSITIVE LOGITS
     decomposition
    0.64
    分解
    0.62
     digits
    0.57
     digit
    0.56
    Digits
    0.56
     decomposed
    0.55
     decompose
    0.55
     decomposing
    0.53
    Digit
    0.52
    digits
    0.52
    Activations Density 0.061%

    No Known Activations