© 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. 154079
    Prev
    Next
    INDEX
    Explanations

    start to phrase construction

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

    explains why

    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
    קו
    0.49
    电机
    0.45
    াহতি
    0.45
    ኬ
    0.44
    漓
    0.44
    氻
    0.44
    ProjectId
    0.44
    बच्चों
    0.44
     eléctricos
    0.44
    طفال
    0.43
    POSITIVE LOGITS
     nong
    0.46
    art
    0.43
    ica
    0.42
     mostly
    0.42
     сначала
    0.42
     cry
    0.41
     B
    0.41
     تفسیر
    0.40
     сама
    0.39
     zuerst
    0.39
    Activations Density 0.000%

    No Known Activations