© 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. 61770
    Prev
    Next
    INDEX
    Explanations

    select formatformat selectselect format are

    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
     آف
    0.46
    avak
    0.44
    üten
    0.43
    }$).
    0.42
    Callable
    0.41
     oov
    0.41
    dött
    0.41
    AllCaps
    0.41
    Missense
    0.40
    talent
    0.40
    POSITIVE LOGITS
     drama
    0.48
     Drama
    0.47
     McCorm
    0.45
    에
    0.45
    トレ
    0.44
     graphique
    0.44
     ৩০০
    0.44
     forcefully
    0.44
     Democracy
    0.43
     potrzeby
    0.43
    Activations Density 0.024%

    No Known Activations