© 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. 3183
    Prev
    Next
    INDEX
    Explanations

    free

    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
     obten
    1.11
    '
    1.10
     aplatis
    1.07
     effectu
    1.06
    r
    1.06
    c
    1.06
     outil
    1.02
     powied
    1.01
     uczni
    1.00
     émotion
    1.00
    POSITIVE LOGITS
     free
    1.30
    ä
    1.25
    z
    1.11
    ة
    1.01
    ing
    0.99
    us
    0.99
     Free
    0.98
    ão
    0.98
     not
    0.97
    óz
    0.95
    Activations Density 0.044%

    No Known Activations