© 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. 40-GEMMASCOPE-2-RES-262K
    7. 220804
    Prev
    Next
    INDEX
    Explanations

    specific keywords following punctuation

    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_262k_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
     möchte
    0.48
    𒊺
    0.46
    ׳
    0.45
    pInBuffer
    0.45
     ใส่
    0.44
     interessiert
    0.44
    PLASMA
    0.44
    ESSMENT
    0.43
    㑒
    0.43
    ياً
    0.43
    POSITIVE LOGITS
    0.49
    Ep
    0.36
    Pos
    0.35
    simpl
    0.35
     Portug
    0.35
    her
    0.34
    ”
    0.34
    begin
    0.34
    Ä
    0.34
    man
    0.34
    Activations Density 0.016%

    No Known Activations