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. 7598
    Prev
    Next
    INDEX
    Explanations

    being and doing

    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
     during
    -1.19
     when
    -1.15
     it
    -1.12
     a
    -1.10
     that
    -1.10
    };
    -1.09
     is
    -1.08
    </tr>
    -1.08
     was
    -1.08
     has
    -1.05
    POSITIVE LOGITS
     themselves
    1.61
     encouraged
    1.32
    becoming
    1.31
     becoming
    1.26
     allowed
    1.26
     increasingly
    1.23
     flock
    1.21
     которых
    1.19
    themselves
    1.16
    heroes
    1.11
    Activations Density 0.071%

    No Known Activations