© 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. 37737
    Prev
    Next
    INDEX
    Explanations

    starts sentences or clauses

    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
    っている
    -1.26
     linkovi
    -1.20
     стане
    -1.18
     ongles
    -1.15
     samti
    -1.09
     میکنه
    -1.09
     Россию
    -1.08
    Namara
    -1.08
    方がいい
    -1.07
    っていた
    -1.05
    POSITIVE LOGITS
     the
    1.58
    <h2>
    1.45
    <h3>
    1.31
     these
    1.23
     other
    1.18
     this
    1.16
     dessas
    1.16
     eigentlichen
    1.13
    <h4>
    1.13
    <h5>
    1.09
    Activations Density 0.257%

    No Known Activations