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

    Neuronpedia

    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. 110923
    Prev
    Next
    INDEX
    Explanations

    capital cities, names, places, dates

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

    the named person given as the direct answer in Q&A-style responses, especially in “The current … is …” formulations.

    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
     النسبيه
    0.37
     Nucleaire
    0.28
    Ბ
    0.27
    ErrorReport
    0.27
    StubCompat
    0.27
     уйнау
    0.26
     verstehen
    0.26
     symbolism
    0.26
     Départ
    0.26
    ICs
    0.26
    POSITIVE LOGITS
    j
    0.31
    b
    0.31
    au
    0.30
    up
    0.30
    uk
    0.30
    5
    0.29
    uv
    0.29
    7
    0.29
    le
    0.29
    h
    0.29
    Activations Density 0.099%

    No Known Activations