© 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. 138753
    Prev
    Next
    INDEX
    Explanations

    informed speculation

    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
    на
    0.59
    at
    0.56
    Otro
    0.53
    atl
    0.51
    owanych
    0.50
    en
    0.49
    config
    0.49
    ת
    0.47
    casa
    0.46
    იზ
    0.46
    POSITIVE LOGITS
     seedling
    0.48
     feral
    0.47
     germination
    0.45
    >′
    0.44
     repeating
    0.44
     curving
    0.44
     সাড়া
    0.44
     globular
    0.44
     potting
    0.43
     comeback
    0.43
    Activations Density 0.004%

    No Known Activations