© 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. 31470
    Prev
    Next
    INDEX
    Explanations

    only followed by 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_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
    骼
    0.64
     wereld
    0.58
    㞖
    0.57
    atini
    0.56
     lingue
    0.56
     mensch
    0.55
     nineties
    0.55
    ță
    0.54
     ottenere
    0.54
     énerg
    0.54
    POSITIVE LOGITS
    EN
    0.69
    ORM
    0.63
    ENE
    0.62
    END
    0.59
    d
    0.59
    E
    0.57
    En
    0.56
    ENS
    0.56
    ANT
    0.55
    ERE
    0.55
    Activations Density 0.009%

    No Known Activations