© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 225225
    Prev
    Next
    INDEX
    Explanations

    your personal data

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

    evaluation ofthan weshould doactually apotential for

    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
    clazz
    0.43
    ροφο
    0.42
    compet
    0.42
    u
    0.41
    ']}
    0.41
    かっこ
    0.41
     combina
    0.41
    c
    0.40
    জাহ
    0.40
     kompet
    0.40
    POSITIVE LOGITS
    leun
    0.49
     ஏனெனில்
    0.46
    erna
    0.46
    स्तानी
    0.46
    incinnati
    0.45
     protest
    0.45
     因为
    0.44
     ध्वनि
    0.44
     предназначен
    0.44
     用于
    0.43
    Activations Density 0.001%

    No Known Activations