© 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. 175838
    Prev
    Next
    INDEX
    Explanations

    collapse accounts

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

    const or across

    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
    ারে
    0.48
    Calc
    0.46
     voisinage
    0.42
    ゴルフ
    0.42
    ن
    0.42
    靶
    0.42
     כ
    0.41
    しばらく
    0.41
    吅
    0.41
    я
    0.41
    POSITIVE LOGITS
    anye
    0.50
     നേടിയ
    0.48
    ാരോഗ്യ
    0.46
     ntawm
    0.46
    ፡፡
    0.45
     रामपुर
    0.45
    ಲ್ಲೂ
    0.45
    aliyet
    0.44
    inderella
    0.44
     Ethiop
    0.44
    Activations Density 0.000%

    No Known Activations