© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117241
    Prev
    Next
    INDEX
    Explanations

    emoticon punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zaki
    -0.94
    以來
    -0.92
    “…
    -0.88
    »?
    -0.86
    losse
    -0.85
    animous
    -0.85
    “...
    -0.84
    Apre
    -0.84
    '!
    -0.82
    InSeconds
    -0.82
    POSITIVE LOGITS
    :
    1.58
     with
    1.45
    :(
    1.31
    :,
    1.28
    :)
    1.16
     (
    1.13
    :.
    1.12
    _(
    1.06
    ://
    1.02
     for
    1.01
    Activations Density 0.025%

    No Known Activations