© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11996
    Prev
    Next
    INDEX
    Explanations

    model trained by Google

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

    This neuron detects first-person self-reference (tokens like "I", "I'm", "I am" and phrases where the speaker describes themselves).

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    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
    ungkinkan
    0.43
    פ
    0.42
     sfrutt
    0.42
     сталки
    0.41
    둴
    0.40
    に近い
    0.39
    ק
    0.39
    כי
    0.39
    esque
    0.38
     भारतात
    0.38
    POSITIVE LOGITS
     fecha
    0.45
    㖷
    0.45
     was
    0.44
     guava
    0.43
     type
    0.43
     date
    0.42
     latest
    0.41
     datetime
    0.41
     apricot
    0.41
     pineapple
    0.39
    Activations Density 0.082%

    No Known Activations