© 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. 46345
    Prev
    Next
    INDEX
    Explanations

    introducing a topic or concept

    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
    EXIT
    0.44
    All
    0.42
    FAN
    0.42
    통
    0.41
     dedicado
    0.40
     vengan
    0.40
    Fan
    0.40
    प
    0.39
     runs
    0.38
    Pupp
    0.38
    POSITIVE LOGITS
    }}=-\
    0.43
    ោយ
    0.43
     mauve
    0.39
     рис
    0.39
     کیل
    0.38
    éz
    0.38
     wê
    0.38
     αν
    0.38
    ümü
    0.38
     വേണ്ടി
    0.37
    Activations Density 0.001%

    No Known Activations