© 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. 16-GEMMASCOPE-2-RES-262K
    7. 85955
    Prev
    Next
    INDEX
    Explanations

    great depths and vastness

    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_16_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
    hwar
    0.65
    빗
    0.65
    pathi
    0.59
    ಋ
    0.57
     khắp
    0.55
    ane
    0.55
    -
    0.54
     Jill
    0.54
     Ane
    0.53
    ں
    0.53
    POSITIVE LOGITS
     seas
    0.71
     abyss
    0.71
     gulf
    0.70
     sea
    0.68
     сте
    0.68
     expanse
    0.67
    ف
    0.67
     océ
    0.66
     indiquée
    0.65
     depths
    0.64
    Activations Density 0.013%

    No Known Activations