© 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. 138005
    Prev
    Next
    INDEX
    Explanations

    astronomical discs

    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
     singularity
    0.49
    İ
    0.49
    ז
    0.48
    AYLOR
    0.47
     discontinuity
    0.45
    і
    0.45
     centrifuged
    0.44
    㗽
    0.44
    వ
    0.44
     shutdown
    0.43
    POSITIVE LOGITS
    ong
    0.67
    ciones
    0.63
    rimidin
    0.62
    cana
    0.60
    cially
    0.59
    íta
    0.59
    homeini
    0.59
    ා
    0.59
    ával
    0.58
    íamos
    0.57
    Activations Density 0.000%

    No Known Activations