© 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. 53-GEMMASCOPE-2-RES-262K
    7. 18906
    Prev
    Next
    INDEX
    Explanations

    [Noun] of [Noun]

    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_53_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
     being
    0.50
    being
    0.47
     itself
    0.46
    ずつ
    0.43
     каждым
    0.42
     each
    0.42
     –
    0.41
     becoming
    0.41
    での
    0.41
    =
    0.41
    POSITIVE LOGITS
     sorts
    1.07
     whom
    0.70
     ceremonies
    0.60
    whom
    0.59
     maladies
    0.55
     Whom
    0.52
     sortes
    0.52
     renown
    0.51
     realms
    0.50
     sort
    0.48
    Activations Density 0.032%

    No Known Activations