© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 10946
    Prev
    Next
    INDEX
    Explanations

    ashwagandha

    np_acts-logits-general · gemini-2.5-flash-lite

    Indian names and words, particularly those containing syllables like "sha", "kh", "har" and "box".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    廡
    -2.50
    acterísticas
    -2.48
    ).”
    -2.30
    鶺
    -2.22
    ⍽
    -2.13
     проблему
    -2.11
    )”.
    -2.09
     машине
    -2.05
    Ꮈ
    -1.99
     Volkes
    -1.98
    POSITIVE LOGITS
    "
    2.53
     thee
    2.31
    ).
    2.20
     ),
    2.03
    ),
    1.99
     pesados
    1.99
     l
    1.98
    зывает
    1.93
     to
    1.90
    a
    1.88
    Activations Density 0.164%

    No Known Activations