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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109910
    Prev
    Next
    INDEX
    Explanations

    mathematical introduction and definitions

    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
     deletes
    -1.13
     notwendigen
    -1.04
    Perhaps
    -0.98
     gewünschten
    -0.97
    さまざま
    -0.97
     melewati
    -0.94
    ücke
    -0.94
     Bestimmungen
    -0.93
    但他
    -0.92
    ⊿
    -0.91
    POSITIVE LOGITS
     given
    1.23
     we
    1.20
    $\
    1.17
    <code>
    1.14
     gegeben
    1.06
     pengar
    1.05
    $-$
    1.04
    <b>
    1.03
    ]}$
    1.03
     $\
    1.01
    Activations Density 0.020%

    No Known Activations