© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 60637
    Prev
    Next
    INDEX
    Explanations

    introducing examples

    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
     sourire
    -1.42
    📽
    -1.36
     estadounid
    -1.36
     anún
    -1.30
     écrivain
    -1.29
     huile
    -1.27
     avantage
    -1.27
     แท
    -1.26
     merveille
    -1.25
     plonge
    -1.24
    POSITIVE LOGITS
     which
    4.03
     but
    3.44
     and
    2.53
     because
    2.19
     while
    2.08
     or
    2.06
     although
    2.02
     whose
    1.98
     as
    1.97
     including
    1.73
    Activations Density 0.021%

    No Known Activations