© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 4318
    Prev
    Next
    INDEX
    Explanations

    words in quotes

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

    quoted terms and keywords

    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_53_width_65k_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
    <s>
    0.48
    and
    0.48
     including
    0.45
    rrh
    0.44
    —
    0.44
    ς
    0.43
     Α
    0.43
    xC
    0.42
    ・
    0.42
    /
    0.41
    POSITIVE LOGITS
    true
    0.71
    golden
    0.68
    dirty
    0.67
    official
    0.66
    normal
    0.65
    false
    0.64
    一带
    0.64
    classic
    0.64
    grandfather
    0.64
    fake
    0.63
    Activations Density 0.259%

    No Known Activations