© 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. 31-GEMMASCOPE-2-RES-262K
    4. 6057
    Prev
    Next
    INDEX
    Explanations

    a 6 Goblin cow

    np_acts-logits-general · gemini-2.5-flash-lite

    the indefinite article in noun-introducing phrases, especially within prompt-like constructions and adjacent function words.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    ní
    0.27
    l
    0.27
    lo
    0.27
     joka
    0.27
    label
    0.26
     {.
    0.26
    bys
    0.26
    rint
    0.26
    stated
    0.26
    cedent
    0.26
    POSITIVE LOGITS
    EM
    0.28
    ANT
    0.27
    OS
    0.27
    辔
    0.26
    Drum
    0.25
    OSH
    0.25
    Fluid
    0.25
    AT
    0.25
    OGRAM
    0.25
    ATIC
    0.24
    Activations Density 0.514%

    No Known Activations