© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 62553
    Prev
    Next
    INDEX
    Explanations

    address this question

    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_31_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
     автобу
    0.49
    னி
    0.47
     kelompok
    0.47
     опреде
    0.46
     группу
    0.46
    
    0.46
     گروه
    0.45
    ья
    0.45
     آباد
    0.45
    antium
    0.45
    POSITIVE LOGITS
    etre
    0.48
    u
    0.43
    kim
    0.41
    bare
    0.41
    h
    0.40
    den
    0.40
     hvil
    0.40
     reta
    0.39
    erate
    0.39
    custom
    0.39
    Activations Density 0.018%

    No Known Activations