© 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-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 2150
    Prev
    Next
    INDEX
    Explanations

    word beginnings and continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Zahlen
    0.31
     അതിനാ
    0.28
     spezielle
    0.27
     റിപ്പോ
    0.27
    макраты
    0.27
     Geschwindigkeit
    0.26
    Einstellungen
    0.26
    詼
    0.26
     जीके
    0.26
     sempl
    0.25
    POSITIVE LOGITS
    us
    0.30
     and
    0.28
    it
    0.28
     or
    0.27
    1
    0.26
     for
    0.25
    can
    0.25
     that
    0.24
     as
    0.24
    ol
    0.24
    Activations Density 0.066%

    No Known Activations