© 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. 22-GEMMASCOPE-RES-131K
    4. 54242
    Prev
    Next
    INDEX
    Explanations

    location separators

    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
    ITÉ
    -1.28
    椟
    -1.26
    ggars
    -1.21
     IBRARY
    -1.19
    providedIn
    -1.16
    quelles
    -1.16
     garant
    -1.16
    Login
    -1.15
     theſe
    -1.14
    tricos
    -1.14
    POSITIVE LOGITS
     and
    1.86
     at
    1.59
     with
    1.35
     before
    1.12
     as
    1.12
     on
    1.05
     to
    1.05
     With
    1.03
     changed
    1.00
     Before
    0.99
    Activations Density 0.000%

    No Known Activations