© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 245
    Prev
    Next
    INDEX
    Explanations

    two layers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𒋛
    0.38
    щаются
    0.37
     mistura
    0.37
     podej
    0.36
     いき
    0.36
    ევს
    0.35
     Direktor
    0.35
     coordenadas
    0.35
    腧
    0.35
    őr
    0.35
    POSITIVE LOGITS
     Rapp
    0.42
     Letters
    0.40
     function
    0.39
     layer
    0.38
     build
    0.37
     Layer
    0.37
     imported
    0.37
     platform
    0.37
     victim
    0.36
     Lines
    0.36
    Activations Density 0.020%

    No Known Activations