© 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. 116429
    Prev
    Next
    INDEX
    Explanations

    practical advice

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

    Instagram trend or illusion

    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
    ції
    0.52
    어졌
    0.49
    𝕣
    0.49
    多次
    0.49
    ল্যান্ডের
    0.49
     또는
    0.48
    цією
    0.48
     utilisée
    0.48
    ії
    0.47
    ⊔
    0.46
    POSITIVE LOGITS
     szen
    0.48
     лист
    0.47
     Sen
    0.46
     механизм
    0.45
     Stefan
    0.45
    NI
    0.45
     proprement
    0.44
    SI
    0.44
     Usuarios
    0.44
    eye
    0.42
    Activations Density 0.000%

    No Known Activations