© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 200030
    Prev
    Next
    INDEX
    Explanations

    making sense

    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
    ﻉ
    0.53
    ellular
    0.50
     sintomi
    0.50
    Ꮺ
    0.50
    বিষয়
    0.50
     कंपनियों
    0.48
    ร
    0.47
    ქვენ
    0.47
    vertrag
    0.47
    ᅨ
    0.46
    POSITIVE LOGITS
     call
    0.53
     as
    0.47
     adjusted
    0.44
     prez
    0.44
     easing
    0.44
     (
    0.44
     llama
    0.44
    إن
    0.43
     Deuter
    0.43
     aligned
    0.43
    Activations Density 0.004%

    No Known Activations