© 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. 69250
    Prev
    Next
    INDEX
    Explanations

    support for claims

    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
    komna
    -1.17
    dä
    -1.11
    uatu
    -1.06
     pengar
    -1.02
    menge
    -1.00
    IBILITIES
    -1.00
    ktiv
    -1.00
    gamento
    -0.99
     получить
    -0.97
    🕗
    -0.95
    POSITIVE LOGITS
     claims
    2.05
     claim
    1.88
     claimed
    1.45
     the
    1.38
     proposed
    1.37
     assertion
    1.35
     belief
    1.30
     that
    1.27
     idea
    1.25
     assertions
    1.25
    Activations Density 0.037%

    No Known Activations