© 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. 101033
    Prev
    Next
    INDEX
    Explanations

    start the, delivered quickly, to crush

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

    ignored, suffer, passing, or insane

    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
    spacePad
    0.57
    WEI
    0.54
    ILLIPS
    0.52
    SRPI
    0.51
     değiştir
    0.50
    CharPtr
    0.50
    ຣ
    0.50
    ENTE
    0.50
    IMENTO
    0.50
    łach
    0.49
    POSITIVE LOGITS
     vs
    0.47
     their
    0.44
    ^
    0.44
     administration
    0.42
    ^-
    0.42
    4
    0.41
    _
    0.41
    ourcing
    0.40
    0
    0.40
     campaign
    0.40
    Activations Density 0.001%

    No Known Activations