© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 28378
    Prev
    Next
    INDEX
    Explanations

    of followed by a noun phrase

    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_22/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
     olvidado
    -1.70
     and
    -1.63
    ſſen
    -1.58
    を行いました
    -1.53
    久し
    -1.46
    lained
    -1.42
     obuv
    -1.42
     tocado
    -1.42
     cinturón
    -1.41
     significativos
    -1.41
    POSITIVE LOGITS
     may
    1.55
     can
    1.50
    v
    1.38
    j
    1.38
    r
    1.37
     them
    1.36
    man
    1.35
     of
    1.30
    av
    1.30
    もちろん
    1.30
    Activations Density 0.032%

    No Known Activations