© 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. 2131
    Prev
    Next
    INDEX
    Explanations

    divisibility and modulo checks

    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
     fotografia
    0.48
    берг
    0.47
    इंद
    0.46
    <unused25>
    0.45
     espécies
    0.45
    }^{+}+\
    0.45
    𒊩
    0.44
    Carroll
    0.43
    Maxim
    0.43
    Hydroxy
    0.43
    POSITIVE LOGITS
     divisible
    0.63
     multiples
    0.54
     divis
    0.48
    偶
    0.46
     modulo
    0.44
     regular
    0.44
     it
    0.43
     number
    0.43
    ities
    0.43
     divisor
    0.43
    Activations Density 0.140%

    No Known Activations