© 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. 139218
    Prev
    Next
    INDEX
    Explanations

    processing models and fees

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

    highlighting content or specific items

    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
     چھوٹے
    0.52
     depois
    0.50
     پس
    0.45
     raindrops
    0.44
    ٠
    0.44
     AFTER
    0.43
     inert
    0.43
     মাথায়
    0.42
     donning
    0.42
    phdr
    0.42
    POSITIVE LOGITS
    ijnen
    0.45
    border
    0.44
    撾
    0.42
    缦
    0.41
    尼斯
    0.40
    bank
    0.40
    iders
    0.39
    ánica
    0.39
    屋
    0.38
    ijn
    0.38
    Activations Density 0.000%

    No Known Activations