© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 22354
    Prev
    Next
    INDEX
    Explanations

    gravity and g

    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
    il
    0.48
    8
    0.47
    k
    0.45
    ben
    0.42
    hint
    0.42
     Uncomment
    0.42
    7
    0.42
    1
    0.42
    d
    0.41
     Chol
    0.40
    POSITIVE LOGITS
     organisms
    0.46
     datth
    0.44
     softens
    0.43
    UCLEAR
    0.43
     dissipative
    0.42
     auricular
    0.42
     pdelay
    0.42
    लपुर
    0.42
     autonomic
    0.42
     loudspeaker
    0.42
    Activations Density 0.000%

    No Known Activations