© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 6837
    Prev
    Next
    INDEX
    Explanations

    animals, nature, and objects

    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
     kuhusu
    0.44
     ១
    0.44
    τικές
    0.40
     gacche
    0.40
     membut
    0.40
     vítimas
    0.40
     endGame
    0.39
    ༡
    0.39
    सामाजिक
    0.38
     informar
    0.38
    POSITIVE LOGITS
     into
    0.43
    esist
    0.41
     still
    0.40
     Spider
    0.38
    oid
    0.37
     tunnel
    0.37
     softly
    0.37
     Valk
    0.37
    als
    0.37
     l
    0.37
    Activations Density 0.296%

    No Known Activations