© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 143257
    Prev
    Next
    INDEX
    Explanations

    options with conditions

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

    negotiating * usually

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     станда
    0.49
    \
    0.45
    }=[
    0.45
     тощо
    0.44
    й
    0.44
     คู่
    0.42
     стандарта
    0.41
     характеристи
    0.41
    subsection
    0.40
    hopper
    0.40
    POSITIVE LOGITS
     recoil
    0.47
    Mâ
    0.46
    乐
    0.45
    plify
    0.45
    ূর্ন
    0.44
    锺
    0.44
     अपन
    0.43
    ζει
    0.43
    ख्ती
    0.43
    ሆኑ
    0.42
    Activations Density 0.001%

    No Known Activations