© 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. 46492
    Prev
    Next
    INDEX
    Explanations

    respective; as; and; manufacture; written

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

    need or combine elements

    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
    Have
    0.44
    }\,
    0.43
     NOTHING
    0.42
    ודי
    0.42
     oblivion
    0.42
     argc
    0.42
    Unser
    0.41
    ანა
    0.40
    Мы
    0.40
     programmer
    0.40
    POSITIVE LOGITS
    ranges
    0.45
    ༩
    0.44
    ческими
    0.43
     sulfon
    0.43
     estan
    0.42
    angels
    0.42
     встречается
    0.42
     folds
    0.40
    变形
    0.40
     thalassemia
    0.40
    Activations Density 0.000%

    No Known Activations