© 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-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118836
    Prev
    Next
    INDEX
    Explanations

    serialization using pickle

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

    structured data format delimiters and metadata field names in JSON, XML, and YAML files.

    oai_token-act-pair · claude-4-5-haikuTriggered by @hkale7
    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
     だっ
    -1.41
    </em>
    -1.27
    ’
    -1.21
    </td>
    -1.20
     This
    -1.16
     économie
    -1.16
    Ἥ
    -1.13
    異なります
    -1.12
    ‐
    -1.11
     Ã
    -1.09
    POSITIVE LOGITS
    '}';
    1.48
     „
    1.48
     leſs
    1.45
    What
    1.40
    뚤
    1.25
     laſt
    1.24
     juſt
    1.24
     neceſſ
    1.23
    How
    1.22
     ſmall
    1.22
    Activations Density 30.812%

    No Known Activations