Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7740
    Prev
    Next
    INDEX
    Explanations

    looks like or stands for

    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
     durabilidad
    -1.15
    下記
    -1.13
     licencias
    -1.05
     когато
    -1.04
     сказали
    -1.01
    ebilir
    -1.00
     disfraces
    -0.99
     bílé
    -0.99
     dům
    -0.99
    резать
    -0.99
    POSITIVE LOGITS
     to
    2.08
     as
    1.23
     without
    1.20
     of
    1.19
    така
    1.12
     sorta
    1.10
    唄
    1.09
     for
    1.08
     into
    1.06
     berkenaan
    1.06
    Activations Density 0.233%

    No Known Activations